NNbenchmark was created during the Google Summer of Code, 2019 as a part of The R Project for Statistical Computing, to verify the convergence of the training algorithms provided in 69 Neural Network R packages available on CRAN to date. Neural networks must be trained with second order algorithms and not with first order algorithms as many packages seem to do.

The purpose of this project is to verify the quality of the training algorithms in R packages that provide neural network of perceptron type (one input layer, one normalized layer, one hidden layer with nonlinear activation function usually tanh(), one normalized layer, one output output layer) for regression purpose i.e. \(NN(X1, ..., Xn) = E[Y]\).



Packages Tested


This GSoC project will conduct a comprehensive survey of all packages that have the “neural network” keyword in thepackage title or in the package description. There are currently 69 packages on CRAN with this keyword.

AMORE ANN2 appnn autoencoder automl BNN
brnn Buddle CaDENCE cld2 cld3 condmixt
DALEX2 DamiaNN deepnet deepNN DNMF elmNNrcpp
ELMR EnsembleBase evclass gamlss.add gcForest GMDH
GMDH2 GMDHreg grnn h2o hybridEnsemble isingLenzMC
keras kerasformula kerasR leabRa learNN LilRhino
MachineShop monmlp neural neuralnet NeuralNetTools NeuralSens
NlinTS nnet nnetpredint nnfor onnx OptimClassifier
OSTSC pnn polyreg predictoR qrnn QuantumOps
quarrint radiant.model rasclass rcane regressoR rminer
rnn RSNNS ruta simpleNeural snnR softmaxreg
Sojourn.Data spnn TeachNet tensorflow tfestimators trackdem
TrafficBDE validann zFactor



Evaluation Criteria


The algorithms were tested on 12 regression datasets (both univariate and multivariate) of varying complexity.

Dataset n_rows n_inputs n_neurons n_parameters
mDette 500 3 5 26
mFriedman 500 5 5 36
mIshigami 500 3 10 51
mRef153 153 5 3 22
uDmod1 51 1 6 19
uDmod2 51 1 5 16
uDreyfus1 51 1 3 10
uDreyfus2 51 1 3 10
uGauss1 250 1 5 16
uGauss2 250 1 4 13
uGauss3 250 1 4 13
uNeuroOne 51 1 2 7

The score for each package was based on the following parameters:

To obtain the final rating, we take a weighted average of these 4 columns (giving more weight to ConvergenceQuality and ConvergenceTIme).



Results


Following are the results of each package per dataset.

Dataset-mDette

event duration RMSE MAE stars params comment package
mDette_AMORE::train_ADAPTgdwm_02 2.281 0.3743 0.2872
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
mDette_ANN2::neuralnetwork_sgd_09 0.999 0.3886 0.2954
iter=4000 lr=0.01 Require fine tuning ANN2
mDette_brnn::brnn_gaussNewton_04 0.141 0.2639 0.2096 *** Different NN brnn
mDette_deepnet::gradientdescent_03 0.750 0.4301 0.3233 numepochs=1000 Bad on univariate datasets deepnet
mDette_h2o::h2o.deeplearning_06 0.515 2.3295 1.6713 maxiter=200 Bad on univariate datasets h2o
mDette_MachineShop::fit.NNetModel_04 0.060 0.4618 0.3469 maxiter = 150 uses nnet MachineShop
mDette_minpacklm::nlsLM_02 0.284 0.1043 0.0832 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
mDette_momlp::monmlp.fit_BFGS_07 0.266 0.3014 0.2372 maxiter = 300 uses optimx momlp
mDette_neural::mlptrain_01 56.402 5.9735 4.4623 maxiter = 1000 classification neural
mDette_neuralnet::neuralnet_slr_03 12.830 0.4553 0.3442 neuralnet
mDette_nlsr::nlxb_05 0.359 0.1665 0.1335 ** maxiter = 150 Require hand-made formulas and scaling nlsr
mDette_nnet::nnet_01 0.063 0.3567 0.2736 maxiter = 150 uses optim BFGS nnet
mDette_qrnn::qrnn.fit_02 0.404 0.0837 0.0579 maxiter = 700 qrnn
mDette_radiantmodel::radiantmodel_06 1.653 0.0703 0.0556 maxiter=10000 preset uses nnet radiantmodel
mDette_rcane::rlm_01 0.000 14.0137 11.3889 maxiter = 1000 linear only rcane
mDette_rminer::fit_01 0.167 0.3595 0.2771 maxiter = 150 rminer
mDette_RSNNS::mlp_SCG_06 1.186 0.4080 0.3029 maxiter = 1000 RSNNS
mDette_simpleNeural::sN.MLPtrain_01 0.000 14.0137 11.3889 maxiter = 1000 for bi- or multiclass classification simpleNeural
mDette_snnR::snnR_02 0.062 0.8399 0.6390 maxiter = 200 better on multi snnR
mDette_softmaxreg::softmaxreg_01 0.016 8.1656 6.5262 maxiter = 1000 softmaxreg
mDette_tsensembler::tsensembler_01 1.676 0.1726 0.1157 maxiter = 150 uses nnet tsensembler
mDette_validann::ann_BFGS_07 1.689 0.2947 0.2241 maxiter = 200 optim validann

Dataset-mFriedman

event duration RMSE MAE stars params comment package
mFriedman_AMORE::train_ADAPTgd_08 0.562 0.0267 0.0214
iter=3500 lr=0.01 Require scaling AMORE
mFriedman_ANN2::neuralnetwork_sgd_04 1.034 0.0162 0.0129
iter=4000 lr=0.01 Require fine tuning ANN2
mFriedman_brnn::brnn_gaussNewton_02 0.203 0.0052 0.0042 *** Different NN brnn
mFriedman_deepnet::gradientdescent_05 0.796 0.0309 0.0242 numepochs=1000 Bad on univariate datasets deepnet
mFriedman_h2o::h2o.deeplearning_09 0.657 0.0327 0.0258 maxiter=200 Bad on univariate datasets h2o
mFriedman_MachineShop::fit.NNetModel_01 0.121 0.0090 0.0071 maxiter = 150 uses nnet MachineShop
mFriedman_minpacklm::nlsLM_03 0.453 0.0051 0.0041 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
mFriedman_momlp::monmlp.fit_BFGS_05 0.338 0.0094 0.0076 maxiter = 300 uses optimx momlp
mFriedman_neural::mlptrain_01 69.804 0.1812 0.1344 maxiter = 1000 classification neural
mFriedman_neuralnet::neuralnet_rprop-_04 12.065 0.0689 0.0490 Erratic on multivariate datasets neuralnet
mFriedman_nlsr::nlxb_02 0.625 0.0047 0.0038 ** maxiter = 150 Require hand-made formulas and scaling nlsr
mFriedman_nnet::nnet_06 0.076 0.0127 0.0102 maxiter = 150 uses optim BFGS nnet
mFriedman_qrnn::qrnn.fit_08 0.426 0.0051 0.0029 maxiter = 700 qrnn
mFriedman_radiantmodel::radiantmodel_02 0.941 0.0041 0.0033 maxiter=10000 preset uses nnet radiantmodel
mFriedman_rcane::rlm_01 0.000 0.6122 0.5654 maxiter = 1000 linear only rcane
mFriedman_rminer::fit_03 0.216 0.0094 0.0074 maxiter = 150 rminer
mFriedman_RSNNS::mlp_SCG_07 1.163 0.0188 0.0147 maxiter = 1000 RSNNS
mFriedman_simpleNeural::sN.MLPtrain_01 0.001 0.6122 0.5654 maxiter = 1000 for bi- or multiclass classification simpleNeural
mFriedman_snnR::snnR_02 0.255 0.0457 0.0357 maxiter = 200 better on multi snnR
mFriedman_softmaxreg::softmaxreg_01 0.000 0.2348 0.1880 maxiter = 1000 softmaxreg
mFriedman_tsensembler::tsensembler_07 1.757 0.0038 0.0028 maxiter = 150 uses nnet tsensembler
mFriedman_validann::ann_BFGS_10 2.195 0.0114 0.0088 maxiter = 200 optim validann

Dataset-mIshigami

event duration RMSE MAE stars params comment package
mIshigami_AMORE::train_ADAPTgd_06 0.984 0.7192 0.5349
iter=3500 lr=0.01 Require scaling AMORE
mIshigami_ANN2::neuralnetwork_sgd_04 1.568 0.6500 0.5050
iter=4000 lr=0.01 Require fine tuning ANN2
mIshigami_brnn::brnn_gaussNewton_04 0.328 0.6583 0.5062 *** Different NN brnn
mIshigami_deepnet::gradientdescent_07 0.937 0.8201 0.6072 numepochs=1000 Bad on univariate datasets deepnet
mIshigami_h2o::h2o.deeplearning_10 0.734 1.0089 0.7433 maxiter=200 Bad on univariate datasets h2o
mIshigami_MachineShop::fit.NNetModel_08 0.324 0.6091 0.4546 maxiter = 150 uses nnet MachineShop
mIshigami_minpacklm::nlsLM_04 1.062 0.6682 0.5170 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
mIshigami_momlp::monmlp.fit_BFGS_08 0.427 0.6225 0.4769 maxiter = 300 uses optimx momlp
mIshigami_neural::mlptrain_05 103.094 2.8352 1.9905 maxiter = 1000 classification neural
mIshigami_neuralnet::neuralnet_rprop+_01 28.040 3.6898 2.9776 Erratic on difficult datasets neuralnet
mIshigami_nlsr::nlxb_06 1.172 0.5895 0.4575 ** maxiter = 150 Require hand-made formulas and scaling nlsr
mIshigami_nnet::nnet_01 0.134 0.7194 0.5373 maxiter = 150 uses optim BFGS nnet
mIshigami_qrnn::qrnn.fit_10 1.070 0.5622 0.3440 maxiter = 700 qrnn
mIshigami_radiantmodel::radiantmodel_01 0.670 0.4761 0.3500 maxiter=10000 preset uses nnet radiantmodel
mIshigami_rcane::rlm_01 0.001 4.9597 3.9131 maxiter = 1000 linear only rcane
mIshigami_rminer::fit_03 0.464 0.6662 0.4870 maxiter = 150 rminer
mIshigami_RSNNS::mlp_SCG_06 1.480 0.6930 0.5113 maxiter = 1000 RSNNS
mIshigami_simpleNeural::sN.MLPtrain_01 0.003 4.9597 3.9131 maxiter = 1000 for bi- or multiclass classification simpleNeural
mIshigami_snnR::snnR_04 0.263 0.7757 0.5560 maxiter = 200 better on multi snnR
mIshigami_softmaxreg::softmaxreg_01 0.000 3.6898 2.9776 maxiter = 1000 softmaxreg
mIshigami_tsensembler::tsensembler_03 1.686 0.2245 0.1666 maxiter = 150 uses nnet tsensembler
mIshigami_validann::ann_BFGS_01 4.642 0.5424 0.3978 maxiter = 200 optim validann

Dataset-mRef153

event duration RMSE MAE stars params comment package
mIshigami_AMORE::train_ADAPTgd_06 0.984 0.7192 0.5349
iter=3500 lr=0.01 Require scaling AMORE
mIshigami_ANN2::neuralnetwork_sgd_04 1.568 0.6500 0.5050
iter=4000 lr=0.01 Require fine tuning ANN2
mIshigami_brnn::brnn_gaussNewton_04 0.328 0.6583 0.5062 *** Different NN brnn
mIshigami_deepnet::gradientdescent_07 0.937 0.8201 0.6072 numepochs=1000 Bad on univariate datasets deepnet
mIshigami_h2o::h2o.deeplearning_10 0.734 1.0089 0.7433 maxiter=200 Bad on univariate datasets h2o
mIshigami_MachineShop::fit.NNetModel_08 0.324 0.6091 0.4546 maxiter = 150 uses nnet MachineShop
mIshigami_minpacklm::nlsLM_04 1.062 0.6682 0.5170 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
mIshigami_momlp::monmlp.fit_BFGS_08 0.427 0.6225 0.4769 maxiter = 300 uses optimx momlp
mIshigami_neural::mlptrain_05 103.094 2.8352 1.9905 maxiter = 1000 classification neural
mIshigami_neuralnet::neuralnet_rprop+_01 28.040 3.6898 2.9776 Erratic on difficult datasets neuralnet
mIshigami_nlsr::nlxb_06 1.172 0.5895 0.4575 ** maxiter = 150 Require hand-made formulas and scaling nlsr
mIshigami_nnet::nnet_01 0.134 0.7194 0.5373 maxiter = 150 uses optim BFGS nnet
mIshigami_qrnn::qrnn.fit_10 1.070 0.5622 0.3440 maxiter = 700 qrnn
mIshigami_radiantmodel::radiantmodel_01 0.670 0.4761 0.3500 maxiter=10000 preset uses nnet radiantmodel
mIshigami_rcane::rlm_01 0.001 4.9597 3.9131 maxiter = 1000 linear only rcane
mIshigami_rminer::fit_03 0.464 0.6662 0.4870 maxiter = 150 rminer
mIshigami_RSNNS::mlp_SCG_06 1.480 0.6930 0.5113 maxiter = 1000 RSNNS
mIshigami_simpleNeural::sN.MLPtrain_01 0.003 4.9597 3.9131 maxiter = 1000 for bi- or multiclass classification simpleNeural
mIshigami_snnR::snnR_04 0.263 0.7757 0.5560 maxiter = 200 better on multi snnR
mIshigami_softmaxreg::softmaxreg_01 0.000 3.6898 2.9776 maxiter = 1000 softmaxreg
mIshigami_tsensembler::tsensembler_03 1.686 0.2245 0.1666 maxiter = 150 uses nnet tsensembler
mIshigami_validann::ann_BFGS_01 4.642 0.5424 0.3978 maxiter = 200 optim validann

Dataset-uDmod1

event start end duration RMSE MAE stars params comment
uDmod1_nlsr::nlxb_01 15:36:49.791 15:36:49.869 0.078 0.0439 0.0356 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_02 15:36:49.869 15:36:49.963 0.094 0.0430 0.0344 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_03 15:36:49.963 15:36:50.041 0.078 0.0433 0.0349 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_04 15:36:50.041 15:36:50.135 0.094 0.0460 0.0364 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_05 15:36:50.135 15:36:50.213 0.078 0.0472 0.0375 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_06 15:36:50.213 15:36:50.291 0.078 0.0950 0.0742 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_07 15:36:50.307 15:36:50.385 0.078 0.0433 0.0349 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_08 15:36:50.385 15:36:50.463 0.078 0.0465 0.0390 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_09 15:36:50.478 15:36:50.556 0.078 0.1012 0.0823 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_nlsr::nlxb_10 15:36:50.556 15:36:50.635 0.079 0.0469 0.0393 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_01 15:46:29.085 15:46:29.147 0.062 0.0433 0.0350 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_02 15:46:29.147 15:46:29.194 0.047 0.5884 0.5069 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_03 15:46:29.194 15:46:29.241 0.047 0.0433 0.0349 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_04 15:46:29.241 15:46:29.303 0.062 0.0418 0.0326 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_05 15:46:29.303 15:46:29.350 0.047 0.0440 0.0355 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_06 15:46:29.350 15:46:29.413 0.063 0.0475 0.0383 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_07 15:46:29.413 15:46:29.460 0.047 0.0797 0.0598 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_08 15:46:29.460 15:46:29.507 0.047 0.5884 0.5069 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_09 15:46:29.507 15:46:29.569 0.062 0.0733 0.0533 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_minpacklm::nlsLM_10 15:46:29.569 15:46:29.616 0.047 0.0433 0.0349 ** maxiter = 150 Require hand-made formulas and scaling
uDmod1_h2o::h2o.deeplearning_01 15:54:04.748 15:54:05.311 0.563 0.3880 0.3357 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_02 15:54:05.311 15:54:05.936 0.625 0.2428 0.1958 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_03 15:54:05.936 15:54:06.483 0.547 0.3503 0.2783 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_04 15:54:06.483 15:54:06.967 0.484 0.3051 0.2466 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_05 15:54:06.967 15:54:07.560 0.593 0.3784 0.3125 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_06 15:54:07.560 15:54:08.060 0.500 0.3151 0.2672 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_07 15:54:08.060 15:54:08.560 0.500 0.3740 0.3073 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_08 15:54:08.560 15:54:09.138 0.578 0.3766 0.3139 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_09 15:54:09.138 15:54:09.716 0.578 0.3696 0.3204 maxiter=200 Bad on univariate datasets
uDmod1_h2o::h2o.deeplearning_10 15:54:09.716 15:54:10.294 0.578 0.3856 0.3063 maxiter=200 Bad on univariate datasets
uDmod1_neuralnet::neuralnet_rprop+_01 18:10:38.981 18:10:40.012 1.031 0.0604 0.0458 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_02 18:10:40.012 18:10:41.699 1.687 0.0615 0.0472 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_03 18:10:41.699 18:10:42.402 0.703 0.0469 0.0380 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_04 18:10:42.402 18:10:43.402 1.000 0.0493 0.0395 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_05 18:10:43.402 18:10:44.261 0.859 0.0616 0.0473 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_01 21:17:55.218 21:18:01.389 6.171 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_02 21:18:01.389 21:18:07.512 6.123 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_03 21:18:07.512 21:18:13.558 6.046 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_04 21:18:13.558 21:18:19.603 6.045 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_05 21:18:19.603 21:18:25.695 6.092 0.5884 0.5069 Fails on difficult datasets
uDmod1_brnn::brnn_gaussNewton_01 10:21:53.726 10:21:53.742 0.016 0.5885 0.5088 *** Different NN
uDmod1_brnn::brnn_gaussNewton_02 10:21:53.742 10:21:53.758 0.016 0.5885 0.5088 *** Different NN
uDmod1_brnn::brnn_gaussNewton_03 10:21:53.758 10:21:53.758 0.000 0.5885 0.5088 *** Different NN
uDmod1_brnn::brnn_gaussNewton_04 10:21:53.758 10:21:53.773 0.015 0.3340 0.2909 *** Different NN
uDmod1_brnn::brnn_gaussNewton_05 10:21:53.773 10:21:53.820 0.047 0.0726 0.0559 *** Different NN
uDmod1_brnn::brnn_gaussNewton_06 10:21:53.820 10:21:53.851 0.031 0.1172 0.0908 *** Different NN
uDmod1_brnn::brnn_gaussNewton_07 10:21:53.851 10:21:53.851 0.000 0.5885 0.5088 *** Different NN
uDmod1_brnn::brnn_gaussNewton_08 10:21:53.851 10:21:53.883 0.032 0.0603 0.0449 *** Different NN
uDmod1_brnn::brnn_gaussNewton_09 10:21:53.883 10:21:53.914 0.031 0.0455 0.0365 *** Different NN
uDmod1_brnn::brnn_gaussNewton_10 10:21:53.914 10:21:53.945 0.031 0.1164 0.0898 *** Different NN
uDmod1_AMORE::train_ADAPTgd_01 13:56:35.894 13:56:36.035 0.141 0.1487 0.1147
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_02 13:56:36.035 13:56:36.175 0.140 0.1300 0.1093
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_03 13:56:36.175 13:56:36.332 0.157 0.1102 0.0913
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_04 13:56:36.332 13:56:36.472 0.140 0.1812 0.1237
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_05 13:56:36.472 13:56:36.628 0.156 0.1617 0.1094
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_06 13:56:36.628 13:56:36.785 0.157 0.1736 0.1241
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_07 13:56:36.785 13:56:36.937 0.152 0.1962 0.1379
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_08 13:56:36.937 13:56:37.092 0.155 0.1366 0.1100
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_09 13:56:37.092 13:56:37.244 0.152 0.1247 0.1027
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgd_10 13:56:37.244 13:56:37.385 0.141 0.1717 0.1157
iter=3500 lr=0.01 Require scaling
uDmod1_AMORE::train_ADAPTgdwm_01 14:16:29.382 14:16:29.913 0.531 0.1034 0.0847
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_02 14:16:29.913 14:16:30.444 0.531 0.1394 0.1006
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_03 14:16:30.444 14:16:30.975 0.531 0.0950 0.0811
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_04 14:16:30.975 14:16:31.507 0.532 0.0949 0.0798
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_05 14:16:31.507 14:16:32.038 0.531 0.0998 0.0838
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_06 14:16:32.038 14:16:32.569 0.531 0.1079 0.0870
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_07 14:16:32.569 14:16:33.131 0.562 0.1383 0.0981
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_08 14:16:33.147 14:16:33.662 0.515 0.1006 0.0829
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_09 14:16:33.662 14:16:34.193 0.531 0.1169 0.0954
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_ADAPTgdwm_10 14:16:34.193 14:16:34.709 0.516 0.1101 0.0921
iter=10000 lr=0.009 momentum=0.8 sigmoid
uDmod1_AMORE::train_BATCHgd_01 14:36:31.616 14:36:33.244 1.628 0.5136 0.4504 iter=7500 lr=0.05 sigmoid very bad
uDmod1_AMORE::train_BATCHgd_02 14:36:33.244 14:36:34.835 1.591 0.4972 0.4339 iter=7500 lr=0.05 sigmoid very bad
uDmod1_AMORE::train_BATCHgd_03 14:36:34.835 14:36:36.290 1.455 0.5132 0.4508 iter=7500 lr=0.05 sigmoid very bad
uDmod1_AMORE::train_BATCHgd_04 14:36:36.290 14:36:37.542 1.252 0.5674 0.5073 iter=7500 lr=0.05 sigmoid very bad
uDmod1_AMORE::train_BATCHgd_05 14:36:37.542 14:36:38.807 1.265 0.4722 0.4093 iter=7500 lr=0.05 sigmoid very bad
uDmod1_AMORE::train_BATCHgdwm_01 15:03:29.098 15:03:32.286 3.188 0.5792 0.5167 iter=9000 lr=0.008 momentum=0.7 tansig Bad and no example
uDmod1_AMORE::train_BATCHgdwm_02 15:03:32.286 15:03:35.281 2.995 0.5754 0.5144 iter=9000 lr=0.008 momentum=0.7 tansig Bad and no example
uDmod1_AMORE::train_BATCHgdwm_03 15:03:35.281 15:03:38.228 2.947 0.5743 0.5138 iter=9000 lr=0.008 momentum=0.7 tansig Bad and no example
uDmod1_AMORE::train_BATCHgdwm_04 15:03:38.228 15:03:41.316 3.088 0.5800 0.5168 iter=9000 lr=0.008 momentum=0.7 tansig Bad and no example
uDmod1_AMORE::train_BATCHgdwm_05 15:03:41.316 15:03:44.318 3.002 0.5794 0.5169 iter=9000 lr=0.008 momentum=0.7 tansig Bad and no example
uDmod1_ANN2::neuralnetwork_sgd_01 16:27:43.593 16:27:43.655 0.062 0.3381 0.2867
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_02 16:27:43.655 16:27:43.718 0.063 0.3319 0.2894
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_03 16:27:43.718 16:27:43.780 0.062 0.3326 0.2900
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_04 16:27:43.796 16:27:43.858 0.062 0.2016 0.1621
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_05 16:27:43.858 16:27:43.921 0.063 0.2065 0.1621
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_06 16:27:43.937 16:27:43.999 0.062 0.2047 0.1608
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_07 16:27:44.015 16:27:44.077 0.062 0.2049 0.1600
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_08 16:27:44.077 16:27:44.140 0.063 0.3399 0.2990
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_09 16:27:44.140 16:27:44.218 0.078 0.3343 0.2928
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_sgd_10 16:27:44.218 16:27:44.280 0.062 0.2063 0.1634
iter=4000 lr=0.01 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_01 16:35:22.249 16:35:22.326 0.077 0.1481 0.1166
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_02 16:35:22.328 16:35:22.403 0.075 0.2052 0.1609
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_03 16:35:22.405 16:35:22.482 0.077 0.2000 0.1599
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_04 16:35:22.484 16:35:22.559 0.075 0.1813 0.1488
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_05 16:35:22.561 16:35:22.638 0.077 0.3380 0.2870
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_06 16:35:22.640 16:35:22.717 0.077 0.1670 0.1336
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_07 16:35:22.719 16:35:22.794 0.075 0.1987 0.1559
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_08 16:35:22.797 16:35:22.873 0.076 0.1846 0.1521
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_09 16:35:22.875 16:35:22.951 0.076 0.1306 0.1072
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_adam_10 16:35:22.953 16:35:23.023 0.070 0.3344 0.2877
iter=4000 lr=0.02 Require fine tuning
uDmod1_ANN2::neuralnetwork_rmsprop_01 16:41:45.528 16:41:45.590 0.062 0.3447 0.2967 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_02 16:41:45.590 16:41:45.653 0.063 0.2279 0.1846 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_03 16:41:45.669 16:41:45.731 0.062 0.2011 0.1592 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_04 16:41:45.731 16:41:45.793 0.062 0.3362 0.2926 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_05 16:41:45.793 16:41:45.872 0.079 0.1988 0.1580 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_06 16:41:45.887 16:41:45.950 0.063 0.3377 0.2951 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_07 16:41:45.950 16:41:46.012 0.062 0.2090 0.1654 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_08 16:41:46.012 16:41:46.090 0.078 0.1834 0.1416 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_09 16:41:46.090 16:41:46.153 0.063 0.1703 0.1331 iter=4000 lr=0.03 Erratic
uDmod1_ANN2::neuralnetwork_rmsprop_10 16:41:46.168 16:41:46.231 0.063 0.2080 0.1657 iter=4000 lr=0.03 Erratic
uDmod1_deepnet::gradientdescent_01 17:29:50.544 17:29:50.669 0.125 0.2715 0.2264 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_02 17:29:50.669 17:29:50.794 0.125 0.3373 0.2886 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_03 17:29:50.794 17:29:50.919 0.125 0.2886 0.2362 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_04 17:29:50.919 17:29:51.044 0.125 0.3009 0.2505 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_05 17:29:51.044 17:29:51.169 0.125 0.2961 0.2528 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_06 17:29:51.169 17:29:51.294 0.125 0.2654 0.2177 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_07 17:29:51.310 17:29:51.435 0.125 0.2938 0.2382 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_08 17:29:51.435 17:29:51.560 0.125 0.2959 0.2524 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_09 17:29:51.560 17:29:51.685 0.125 0.2569 0.2049 numepochs=1000 Bad on univariate datasets
uDmod1_deepnet::gradientdescent_10 17:29:51.685 17:29:51.810 0.125 0.3055 0.2500 numepochs=1000 Bad on univariate datasets
uDmod1_MachineShop::fit.NNetModel_01 03:19:13.206 03:19:13.223 0.017 0.1133 0.0713 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_02 03:19:13.223 03:19:13.223 0.000 0.0627 0.0503 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_03 03:19:13.239 03:19:13.239 0.000 0.0449 0.0368 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_04 03:19:13.239 03:19:13.257 0.018 0.0928 0.0667 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_05 03:19:13.258 03:19:13.267 0.009 0.0645 0.0513 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_06 03:19:13.269 03:19:13.276 0.007 0.1114 0.0833 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_07 03:19:13.276 03:19:13.276 0.000 0.0963 0.0758 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_08 03:19:13.276 03:19:13.291 0.015 0.0443 0.0365 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_09 03:19:13.291 03:19:13.291 0.000 0.0660 0.0533 maxiter = 150 uses nnet
uDmod1_MachineShop::fit.NNetModel_10 03:19:13.307 03:19:13.307 0.000 0.0447 0.0363 maxiter = 150 uses nnet
uDmod1_momlp::monmlp.fit_BFGS_01 03:19:58.197 03:19:58.396 0.199 0.0557 0.0451 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_02 03:19:58.396 03:19:58.597 0.201 0.0520 0.0412 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_03 03:19:58.598 03:19:58.812 0.214 0.0503 0.0411 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_04 03:19:58.814 03:19:59.027 0.213 0.1029 0.0834 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_05 03:19:59.028 03:19:59.221 0.193 0.0905 0.0697 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_06 03:19:59.222 03:19:59.388 0.166 0.0877 0.0654 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_07 03:19:59.390 03:19:59.568 0.178 0.0502 0.0400 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_08 03:19:59.568 03:19:59.726 0.158 0.0636 0.0491 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_09 03:19:59.726 03:19:59.912 0.186 0.0659 0.0515 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_BFGS_10 03:19:59.913 03:20:00.078 0.165 0.0504 0.0405 maxiter = 300 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_01 03:21:00.058 03:21:00.337 0.279 0.2013 0.1628 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_02 03:21:00.337 03:21:00.679 0.342 0.1722 0.1318 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_03 03:21:00.695 03:21:01.068 0.373 0.2230 0.1769 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_04 03:21:01.069 03:21:01.387 0.318 0.2177 0.1694 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_05 03:21:01.387 03:21:01.717 0.330 0.2824 0.2180 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_06 03:21:01.717 03:21:02.075 0.358 0.1471 0.1172 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_07 03:21:02.075 03:21:02.403 0.328 0.2066 0.1492 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_08 03:21:02.403 03:21:02.755 0.352 0.2237 0.1817 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_09 03:21:02.755 03:21:03.022 0.267 0.2876 0.2455 maxiter = 10000 uses optimx
uDmod1_momlp::monmlp.fit_Nelder-Mead_10 03:21:03.022 03:21:03.368 0.346 0.1639 0.1310 maxiter = 10000 uses optimx
uDmod1_neural::mlptrain_01 03:41:46.534 03:41:51.499 4.965 0.4647 0.3589 maxiter = 1000 classification
uDmod1_neural::mlptrain_02 03:41:51.499 03:41:56.442 4.943 0.4647 0.3582 maxiter = 1000 classification
uDmod1_neural::mlptrain_03 03:41:56.442 03:42:01.338 4.896 0.4647 0.3594 maxiter = 1000 classification
uDmod1_neural::mlptrain_04 03:42:01.353 03:42:06.289 4.936 0.4647 0.3592 maxiter = 1000 classification
uDmod1_neural::mlptrain_05 03:42:06.289 03:42:11.354 5.065 0.4647 0.3583 maxiter = 1000 classification
uDmod1_neuralnet::neuralnet_backprop_01 03:52:09.894 03:52:14.210 4.316 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_02 03:52:14.211 03:52:18.614 4.403 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_03 03:52:18.615 03:52:22.875 4.260 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_04 03:52:22.891 03:52:27.134 4.243 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_backprop_05 03:52:27.150 03:52:31.408 4.258 0.5884 0.5069 Fails on difficult datasets
uDmod1_neuralnet::neuralnet_rprop-_01 03:58:52.308 03:58:53.439 1.131 0.0614 0.0469 Erratic on multivariate datasets
uDmod1_neuralnet::neuralnet_rprop-_02 03:58:53.439 03:58:55.384 1.945 0.0505 0.0422 Erratic on multivariate datasets
uDmod1_neuralnet::neuralnet_rprop-_03 03:58:55.384 03:58:57.662 2.278 0.0511 0.0413 Erratic on multivariate datasets
uDmod1_neuralnet::neuralnet_rprop-_04 03:58:57.663 03:58:59.247 1.584 0.0619 0.0496 Erratic on multivariate datasets
uDmod1_neuralnet::neuralnet_rprop-_05 03:58:59.249 03:59:00.497 1.248 0.0468 0.0384 Erratic on multivariate datasets
uDmod1_neuralnet::neuralnet_sag_01 04:11:20.663 04:11:26.040 5.377 0.5884 0.5069
uDmod1_neuralnet::neuralnet_sag_02 04:11:26.040 04:11:31.529 5.489 0.5884 0.5069
uDmod1_neuralnet::neuralnet_sag_03 04:11:31.529 04:11:37.130 5.601 0.5884 0.5069
uDmod1_neuralnet::neuralnet_sag_04 04:11:37.130 04:11:42.512 5.382 0.5884 0.5069
uDmod1_neuralnet::neuralnet_sag_05 04:11:42.512 04:11:47.945 5.433 0.5884 0.5069
uDmod1_neuralnet::neuralnet_slr_01 04:19:14.053 04:19:14.378 0.325 0.0602 0.0456
uDmod1_neuralnet::neuralnet_slr_02 04:19:14.378 04:19:14.966 0.588 0.0539 0.0431
uDmod1_neuralnet::neuralnet_slr_03 04:19:14.966 04:19:15.615 0.649 0.0471 0.0382
uDmod1_neuralnet::neuralnet_slr_04 04:19:15.615 04:19:19.680 4.065 0.0588 0.0457
uDmod1_neuralnet::neuralnet_slr_05 04:19:19.680 04:19:20.949 1.269 0.0510 0.0414
uDmod1_neuralnet::neuralnet_rprop+_01 04:24:31.266 04:24:32.040 0.774 0.0458 0.0360 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_02 04:24:32.042 04:24:33.620 1.578 0.0582 0.0439 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_03 04:24:33.620 04:24:37.195 3.575 0.1152 0.0863 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_04 04:24:37.195 04:24:42.531 5.336 0.5884 0.5069 Erratic on difficult datasets
uDmod1_neuralnet::neuralnet_rprop+_05 04:24:42.531 04:24:43.894 1.363 0.0500 0.0394 Erratic on difficult datasets
uDmod1_nnet::nnet_01 04:25:32.861 04:25:32.868 0.007 0.0847 0.0592 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_02 04:25:32.869 04:25:32.877 0.008 0.0451 0.0370 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_03 04:25:32.878 04:25:32.884 0.006 0.1103 0.0703 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_04 04:25:32.885 04:25:32.892 0.007 0.0458 0.0365 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_05 04:25:32.893 04:25:32.900 0.007 0.1667 0.1179 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_06 04:25:32.902 04:25:32.909 0.007 0.1131 0.0812 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_07 04:25:32.910 04:25:32.918 0.008 0.0480 0.0395 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_08 04:25:32.919 04:25:32.926 0.007 0.0442 0.0361 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_09 04:25:32.928 04:25:32.935 0.007 0.1014 0.0792 maxiter = 150 uses optim BFGS
uDmod1_nnet::nnet_10 04:25:32.937 04:25:32.944 0.007 0.0827 0.0628 maxiter = 150 uses optim BFGS
uDmod1_qrnn::qrnn.fit_01 04:25:55.062 04:25:55.253 0.191 0.0663 0.0448 maxiter = 700
uDmod1_qrnn::qrnn.fit_02 04:25:55.253 04:25:55.636 0.383 0.1365 0.0715 maxiter = 700
uDmod1_qrnn::qrnn.fit_03 04:25:55.636 04:25:55.835 0.199 0.0910 0.0634 maxiter = 700
uDmod1_qrnn::qrnn.fit_04 04:25:55.835 04:25:56.026 0.191 0.0491 0.0326 maxiter = 700
uDmod1_qrnn::qrnn.fit_05 04:25:56.042 04:25:56.241 0.199 0.1353 0.0711 maxiter = 700
uDmod1_qrnn::qrnn.fit_06 04:25:56.241 04:25:56.474 0.233 0.1314 0.0675 maxiter = 700
uDmod1_qrnn::qrnn.fit_07 04:25:56.474 04:25:56.846 0.372 0.0676 0.0434 maxiter = 700
uDmod1_qrnn::qrnn.fit_08 04:25:56.846 04:25:57.162 0.316 0.1164 0.0601 maxiter = 700
uDmod1_qrnn::qrnn.fit_09 04:25:57.162 04:25:57.550 0.388 0.0471 0.0327 maxiter = 700
uDmod1_qrnn::qrnn.fit_10 04:25:57.550 04:25:57.810 0.260 0.0609 0.0382 maxiter = 700
uDmod1_radiantmodel::radiantmodel_01 04:27:35.597 04:27:35.634 0.037 0.1029 0.0782 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_02 04:27:35.636 04:27:35.672 0.036 0.0456 0.0363 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_03 04:27:35.673 04:27:35.700 0.027 0.1168 0.0786 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_04 04:27:35.701 04:27:35.733 0.032 0.1124 0.0705 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_05 04:27:35.734 04:27:35.787 0.053 0.0433 0.0350 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_06 04:27:35.788 04:27:35.824 0.036 0.0459 0.0363 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_07 04:27:35.825 04:27:35.865 0.040 0.0403 0.0307 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_08 04:27:35.866 04:27:35.909 0.043 0.0433 0.0349 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_09 04:27:35.910 04:27:35.967 0.057 0.0433 0.0349 maxiter=10000 preset uses nnet
uDmod1_radiantmodel::radiantmodel_10 04:27:35.967 04:27:35.999 0.032 0.0433 0.0350 maxiter=10000 preset uses nnet
uDmod1_rcane::rlm_01 04:27:45.144 04:27:45.145 0.001 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_02 04:27:45.147 04:27:45.148 0.001 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_03 04:27:45.149 04:27:45.150 0.001 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_04 04:27:45.151 04:27:45.152 0.001 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_05 04:27:45.153 04:27:45.154 0.001 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_06 04:27:45.156 04:27:45.158 0.002 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_07 04:27:45.158 04:27:45.158 0.000 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_08 04:27:45.158 04:27:45.158 0.000 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_09 04:27:45.158 04:27:45.158 0.000 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rcane::rlm_10 04:27:45.158 04:27:45.158 0.000 0.5885 0.5088 maxiter = 1000 linear only
uDmod1_rminer::fit_01 04:27:57.919 04:27:57.936 0.017 0.0588 0.0434 maxiter = 150
uDmod1_rminer::fit_02 04:27:57.937 04:27:57.955 0.018 0.0445 0.0362 maxiter = 150
uDmod1_rminer::fit_03 04:27:57.956 04:27:57.974 0.018 0.0817 0.0695 maxiter = 150
uDmod1_rminer::fit_04 04:27:57.975 04:27:57.991 0.016 0.0579 0.0475 maxiter = 150
uDmod1_rminer::fit_05 04:27:57.993 04:27:58.010 0.017 0.0458 0.0364 maxiter = 150
uDmod1_rminer::fit_06 04:27:58.012 04:27:58.030 0.018 0.0449 0.0366 maxiter = 150
uDmod1_rminer::fit_07 04:27:58.031 04:27:58.050 0.019 0.0452 0.0358 maxiter = 150
uDmod1_rminer::fit_08 04:27:58.052 04:27:58.068 0.016 0.0469 0.0375 maxiter = 150
uDmod1_rminer::fit_09 04:27:58.070 04:27:58.089 0.019 0.0467 0.0378 maxiter = 150
uDmod1_rminer::fit_10 04:27:58.090 04:27:58.108 0.018 0.0434 0.0341 maxiter = 150
uDmod1_RSNNS::mlp_BackpropBatch_01 04:32:15.327 04:32:16.287 0.960 0.3805 0.3333 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_02 04:32:16.288 04:32:17.093 0.805 0.3194 0.2731 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_03 04:32:17.094 04:32:17.896 0.802 0.3076 0.2587 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_04 04:32:17.896 04:32:18.704 0.808 0.3368 0.2916 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_05 04:32:18.704 04:32:19.497 0.793 0.3328 0.2882 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_06 04:32:19.497 04:32:20.444 0.947 0.2564 0.1988 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_07 04:32:20.444 04:32:21.230 0.786 0.3781 0.3317 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_08 04:32:21.230 04:32:22.045 0.815 0.2913 0.2419 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_09 04:32:22.047 04:32:22.832 0.785 0.3322 0.2874 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropBatch_10 04:32:22.832 04:32:23.644 0.812 0.2746 0.2243 maxiter = 10000
uDmod1_RSNNS::mlp_BackpropChunk_01 04:34:51.241 04:34:51.324 0.083 0.2654 0.2024 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_02 04:34:51.325 04:34:51.407 0.082 0.1944 0.1641 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_03 04:34:51.407 04:34:51.485 0.078 0.1600 0.1188 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_04 04:34:51.485 04:34:51.579 0.094 0.1599 0.1221 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_05 04:34:51.579 04:34:51.822 0.243 0.2258 0.1742 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_06 04:34:51.822 04:34:51.897 0.075 0.1368 0.0923 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_07 04:34:51.912 04:34:51.990 0.078 0.1924 0.1529 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_08 04:34:51.990 04:34:52.068 0.078 0.1693 0.1357 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_09 04:34:52.084 04:34:52.157 0.073 0.2190 0.1725 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropChunk_10 04:34:52.157 04:34:52.248 0.091 0.2115 0.1607 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_01 04:35:28.577 04:35:28.659 0.082 0.2163 0.1720 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_02 04:35:28.660 04:35:28.747 0.087 0.1320 0.0949 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_03 04:35:28.748 04:35:28.830 0.082 0.1634 0.1272 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_04 04:35:28.831 04:35:28.918 0.087 0.1454 0.1022 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_05 04:35:28.920 04:35:29.007 0.087 0.1787 0.1505 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_06 04:35:29.008 04:35:29.089 0.081 0.2018 0.1714 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_07 04:35:29.091 04:35:29.178 0.087 0.1982 0.1536 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_08 04:35:29.179 04:35:29.261 0.082 0.2053 0.1564 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_09 04:35:29.263 04:35:29.342 0.079 0.1701 0.1284 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropMomentum_10 04:35:29.342 04:35:29.436 0.094 0.2109 0.1597 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_01 04:36:06.630 04:36:06.712 0.082 0.1976 0.1563 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_02 04:36:06.714 04:36:06.791 0.077 0.1769 0.1390 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_03 04:36:06.791 04:36:06.877 0.086 0.1871 0.1533 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_04 04:36:06.877 04:36:06.959 0.082 0.1423 0.1123 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_05 04:36:06.959 04:36:07.053 0.094 0.1524 0.1154 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_06 04:36:07.053 04:36:07.131 0.078 0.1507 0.1133 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_07 04:36:07.131 04:36:07.222 0.091 0.1310 0.0920 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_08 04:36:07.222 04:36:07.316 0.094 0.1489 0.1164 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_09 04:36:07.316 04:36:07.393 0.077 0.1595 0.1153 maxiter = 1000
uDmod1_RSNNS::mlp_BackpropWeightDecay_10 04:36:07.408 04:36:07.487 0.079 0.1557 0.1155 maxiter = 1000
uDmod1_RSNNS::mlp_Quickprop_01 04:40:35.840 04:40:36.657 0.817 0.5884 0.5068 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_02 04:40:36.658 04:40:37.596 0.938 0.5884 0.5069 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_03 04:40:37.596 04:40:38.393 0.797 0.5884 0.5070 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_04 04:40:38.393 04:40:39.209 0.816 0.5884 0.5071 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_05 04:40:39.209 04:40:39.998 0.789 0.5884 0.5069 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_06 04:40:39.999 04:40:40.957 0.958 0.5885 0.5075 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_07 04:40:40.958 04:40:41.827 0.869 0.5884 0.5068 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_08 04:40:41.828 04:40:42.606 0.778 0.5884 0.5069 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_09 04:40:42.607 04:40:43.415 0.808 0.5885 0.5075 maxiter = 10000
uDmod1_RSNNS::mlp_Quickprop_10 04:40:43.415 04:40:44.215 0.800 0.5884 0.5070 maxiter = 10000
uDmod1_RSNNS::mlp_Rprop_01 04:43:20.964 04:43:21.042 0.078 0.0667 0.0515 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_02 04:43:21.042 04:43:21.133 0.091 0.1403 0.1012 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_03 04:43:21.133 04:43:21.211 0.078 0.1204 0.0819 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_04 04:43:21.211 04:43:21.302 0.091 0.0620 0.0486 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_05 04:43:21.302 04:43:21.380 0.078 0.1315 0.0833 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_06 04:43:21.380 04:43:21.473 0.093 0.1240 0.0828 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_07 04:43:21.473 04:43:21.552 0.079 0.4062 0.2843 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_08 04:43:21.552 04:43:21.642 0.090 0.1330 0.0861 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_09 04:43:21.642 04:43:21.726 0.084 0.0505 0.0400 maxiter = 1000
uDmod1_RSNNS::mlp_Rprop_10 04:43:21.726 04:43:21.804 0.078 0.3232 0.2421 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_01 04:44:13.711 04:44:13.840 0.129 0.1720 0.1301 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_02 04:44:13.840 04:44:13.981 0.141 0.0846 0.0659 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_03 04:44:13.981 04:44:14.121 0.140 0.1293 0.0883 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_04 04:44:14.121 04:44:14.262 0.141 0.1396 0.1038 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_05 04:44:14.262 04:44:14.400 0.138 0.1414 0.1023 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_06 04:44:14.400 04:44:14.540 0.140 0.0569 0.0466 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_07 04:44:14.540 04:44:14.634 0.094 0.4021 0.3555 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_08 04:44:14.634 04:44:14.753 0.119 0.1967 0.1424 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_09 04:44:14.753 04:44:14.862 0.109 0.1458 0.1040 maxiter = 1000
uDmod1_RSNNS::mlp_SCG_10 04:44:14.862 04:44:15.003 0.141 0.1122 0.0825 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_01 04:44:58.260 04:44:58.343 0.083 0.1763 0.1290 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_02 04:44:58.343 04:44:58.429 0.086 0.1936 0.1454 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_03 04:44:58.430 04:44:58.515 0.085 0.1844 0.1375 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_04 04:44:58.515 04:44:58.599 0.084 0.2419 0.1921 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_05 04:44:58.601 04:44:58.688 0.087 0.1657 0.1228 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_06 04:44:58.689 04:44:58.770 0.081 0.1436 0.1074 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_07 04:44:58.772 04:44:58.858 0.086 0.1442 0.1115 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_08 04:44:58.859 04:44:58.945 0.086 0.2082 0.1756 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_09 04:44:58.947 04:44:59.029 0.082 0.2326 0.2057 maxiter = 1000
uDmod1_RSNNS::mlp_Std_Backpropagation_10 04:44:59.030 04:44:59.116 0.086 0.2260 0.1941 maxiter = 1000
uDmod1_simpleNeural::sN.MLPtrain_01 04:49:29.834 04:49:30.018 0.184 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_02 04:49:30.020 04:49:30.208 0.188 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_03 04:49:30.209 04:49:30.386 0.177 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_04 04:49:30.386 04:49:30.574 0.188 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_05 04:49:30.574 04:49:30.758 0.184 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_06 04:49:30.758 04:49:30.957 0.199 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_07 04:49:30.961 04:49:31.150 0.189 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_08 04:49:31.150 04:49:31.343 0.193 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_09 04:49:31.345 04:49:31.521 0.176 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_simpleNeural::sN.MLPtrain_10 04:49:31.521 04:49:31.714 0.193 0.5846 0.5052 maxiter = 1000 for bi- or multiclass classification
uDmod1_snnR::snnR_01 04:49:59.086 04:49:59.111 0.025 0.3595 0.3116 maxiter = 200 better on multi
uDmod1_snnR::snnR_02 04:49:59.127 04:49:59.143 0.016 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_03 04:49:59.143 04:49:59.172 0.029 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_04 04:49:59.174 04:49:59.194 0.020 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_05 04:49:59.194 04:49:59.258 0.064 0.3595 0.3116 maxiter = 200 better on multi
uDmod1_snnR::snnR_06 04:49:59.259 04:49:59.271 0.012 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_07 04:49:59.287 04:49:59.323 0.036 0.3595 0.3116 maxiter = 200 better on multi
uDmod1_snnR::snnR_08 04:49:59.325 04:49:59.344 0.019 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_09 04:49:59.345 04:49:59.364 0.019 0.2927 0.2512 maxiter = 200 better on multi
uDmod1_snnR::snnR_10 04:49:59.364 04:49:59.407 0.043 0.3595 0.3116 maxiter = 200 better on multi
uDmod1_softmaxreg::softmaxreg_01 04:50:01.720 04:50:01.720 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_02 04:50:01.720 04:50:01.720 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_03 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_04 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_05 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_06 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_07 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_08 04:50:01.736 04:50:01.736 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_09 04:50:01.736 04:50:01.751 0.015 0.5884 0.5069 maxiter = 1000
uDmod1_softmaxreg::softmaxreg_10 04:50:01.751 04:50:01.751 0.000 0.5884 0.5069 maxiter = 1000
uDmod1_tsensembler::tsensembler_01 04:50:59.194 04:50:59.286 0.092 0.1147 0.0890 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_02 04:50:59.287 04:50:59.405 0.118 0.1147 0.0890 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_03 04:50:59.405 04:50:59.507 0.102 0.1147 0.0890 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_04 04:50:59.508 04:50:59.587 0.079 0.1149 0.0891 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_05 04:50:59.589 04:50:59.659 0.070 0.1147 0.0891 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_06 04:50:59.661 04:50:59.728 0.067 0.1148 0.0893 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_07 04:50:59.729 04:50:59.794 0.065 0.1146 0.0890 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_08 04:50:59.794 04:50:59.844 0.050 0.2116 0.1633 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_09 04:50:59.844 04:50:59.951 0.107 0.1147 0.0890 maxiter = 150 uses nnet
uDmod1_tsensembler::tsensembler_10 04:50:59.953 04:51:00.022 0.069 0.1147 0.0890 maxiter = 150 uses nnet
uDmod1_validann::ann_BFGS_01 04:53:24.869 04:53:25.578 0.709 0.0532 0.0444 maxiter = 200 optim
uDmod1_validann::ann_BFGS_02 04:53:25.579 04:53:26.286 0.707 0.0460 0.0372 maxiter = 200 optim
uDmod1_validann::ann_BFGS_03 04:53:26.291 04:53:26.995 0.704 0.1131 0.0715 maxiter = 200 optim
uDmod1_validann::ann_BFGS_04 04:53:26.997 04:53:27.700 0.703 0.0569 0.0447 maxiter = 200 optim
uDmod1_validann::ann_BFGS_05 04:53:27.701 04:53:28.409 0.708 0.1144 0.0785 maxiter = 200 optim
uDmod1_validann::ann_BFGS_06 04:53:28.409 04:53:29.113 0.704 0.1156 0.0782 maxiter = 200 optim
uDmod1_validann::ann_BFGS_07 04:53:29.114 04:53:29.826 0.712 0.1174 0.0776 maxiter = 200 optim
uDmod1_validann::ann_BFGS_08 04:53:29.828 04:53:30.523 0.695 0.0522 0.0368 maxiter = 200 optim
uDmod1_validann::ann_BFGS_09 04:53:30.523 04:53:31.224 0.701 0.0885 0.0689 maxiter = 200 optim
uDmod1_validann::ann_BFGS_10 04:53:31.224 04:53:31.930 0.706 0.0420 0.0326 maxiter = 200 optim
uDmod1_validann::ann_CG_01 05:03:15.638 05:03:20.274 4.636 0.0580 0.0478 maxiter = 1000 optim
uDmod1_validann::ann_CG_02 05:03:20.274 05:03:24.900 4.626 0.0600 0.0495 maxiter = 1000 optim
uDmod1_validann::ann_CG_03 05:03:24.901 05:03:29.529 4.628 0.0732 0.0612 maxiter = 1000 optim
uDmod1_validann::ann_CG_04 05:03:29.529 05:03:34.225 4.696 0.0506 0.0406 maxiter = 1000 optim
uDmod1_validann::ann_CG_05 05:03:34.225 05:03:38.826 4.601 0.0649 0.0521 maxiter = 1000 optim
uDmod1_validann::ann_CG_06 05:03:38.828 05:03:43.452 4.624 0.0792 0.0632 maxiter = 1000 optim
uDmod1_validann::ann_CG_07 05:03:43.452 05:03:48.102 4.650 0.1111 0.0687 maxiter = 1000 optim
uDmod1_validann::ann_CG_08 05:03:48.105 05:03:52.687 4.582 0.0522 0.0431 maxiter = 1000 optim
uDmod1_validann::ann_CG_09 05:03:52.687 05:03:57.295 4.608 0.0817 0.0668 maxiter = 1000 optim
uDmod1_validann::ann_CG_10 05:03:57.295 05:04:02.003 4.708 0.0496 0.0398 maxiter = 1000 optim
uDmod1_validann::ann_L-BFGS-B_01 05:09:37.070 05:09:37.820 0.750 0.1422 0.1054 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_02 05:09:37.835 05:09:38.623 0.788 0.0668 0.0554 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_03 05:09:38.624 05:09:39.462 0.838 0.0726 0.0614 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_04 05:09:39.478 05:09:40.255 0.777 0.0665 0.0493 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_05 05:09:40.256 05:09:41.039 0.783 0.0520 0.0427 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_06 05:09:41.040 05:09:41.833 0.793 0.1158 0.0756 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_07 05:09:41.834 05:09:42.706 0.872 0.1173 0.0777 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_08 05:09:42.706 05:09:43.531 0.825 0.1233 0.0831 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_09 05:09:43.531 05:09:44.328 0.797 0.1064 0.0817 maxiter = 200 optim
uDmod1_validann::ann_L-BFGS-B_10 05:09:44.328 05:09:45.123 0.795 0.0807 0.0632 maxiter = 200 optim
uDmod1_validann::ann_Nelder-Mead_01 05:11:53.062 05:11:53.999 0.937 0.1921 0.1499 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_02 05:11:53.999 05:11:55.164 1.165 0.1857 0.1512 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_03 05:11:55.166 05:11:56.346 1.180 0.2251 0.1750 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_04 05:11:56.346 05:11:57.504 1.158 0.1858 0.1527 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_05 05:11:57.504 05:11:58.795 1.291 0.1889 0.1437 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_06 05:11:58.796 05:11:59.937 1.141 0.1497 0.1230 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_07 05:11:59.939 05:12:01.092 1.153 0.3195 0.2348 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_08 05:12:01.092 05:12:02.170 1.078 0.2090 0.1549 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_09 05:12:02.170 05:12:03.070 0.900 0.1782 0.1417 maxiter = 10000 optim
uDmod1_validann::ann_Nelder-Mead_10 05:12:03.071 05:12:04.253 1.182 0.2264 0.1624 maxiter = 10000 optim
uDmod1_validann::ann_SANN_01 05:14:06.814 05:14:07.894 1.080 0.3134 0.2526 maxiter = 10000 optim
uDmod1_validann::ann_SANN_02 05:14:07.895 05:14:08.846 0.951 0.2621 0.2201 maxiter = 10000 optim
uDmod1_validann::ann_SANN_03 05:14:08.847 05:14:09.793 0.946 0.2560 0.2046 maxiter = 10000 optim
uDmod1_validann::ann_SANN_04 05:14:09.795 05:14:10.733 0.938 0.3248 0.2664 maxiter = 10000 optim
uDmod1_validann::ann_SANN_05 05:14:10.733 05:14:11.688 0.955 0.2888 0.2387 maxiter = 10000 optim
uDmod1_validann::ann_SANN_06 05:14:11.688 05:14:12.660 0.972 0.2870 0.2420 maxiter = 10000 optim
uDmod1_validann::ann_SANN_07 05:14:12.661 05:14:13.621 0.960 0.3616 0.2892 maxiter = 10000 optim
uDmod1_validann::ann_SANN_08 05:14:13.622 05:14:14.562 0.940 0.2756 0.2334 maxiter = 10000 optim
uDmod1_validann::ann_SANN_09 05:14:14.577 05:14:15.531 0.954 0.3037 0.2475 maxiter = 10000 optim
uDmod1_validann::ann_SANN_10 05:14:15.531 05:14:16.483 0.952 0.3061 0.2618 maxiter = 10000 optim

Dataset-uDmod2

event duration RMSE MAE stars params comment package
uDmod2_AMORE::train_ADAPTgdwm_09 0.478 0.0499 0.0411
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uDmod2_ANN2::neuralnetwork_adam_10 0.070 0.0720 0.0576
iter=4000 lr=0.02 Require fine tuning ANN2
uDmod2_brnn::brnn_gaussNewton_03 0.031 0.0438 0.0351 *** Different NN brnn
uDmod2_deepnet::gradientdescent_03 0.109 0.1427 0.1140 numepochs=1000 Bad on univariate datasets deepnet
uDmod2_h2o::h2o.deeplearning_05 0.469 0.1970 0.1619 maxiter=200 Bad on univariate datasets h2o
uDmod2_MachineShop::fit.NNetModel_07 0.000 0.0406 0.0331 maxiter = 150 uses nnet MachineShop
uDmod2_minpacklm::nlsLM_03 0.015 0.0427 0.0333 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uDmod2_momlp::monmlp.fit_BFGS_09 0.164 0.0473 0.0378 maxiter = 300 uses optimx momlp
uDmod2_neural::mlptrain_01 4.489 0.3865 0.2679 maxiter = 1000 classification neural
uDmod2_neuralnet::neuralnet_rprop+_05 2.296 0.0417 0.0334 Erratic on difficult datasets neuralnet
uDmod2_nlsr::nlxb_10 0.078 0.0405 0.0327 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uDmod2_nnet::nnet_07 0.008 0.0406 0.0324 maxiter = 150 uses optim BFGS nnet
uDmod2_qrnn::qrnn.fit_06 0.556 0.0449 0.0305 maxiter = 700 qrnn
uDmod2_radiantmodel::radiantmodel_01 0.028 0.0405 0.0327 maxiter=10000 preset uses nnet radiantmodel
uDmod2_rcane::rlm_01 0.015 0.5179 0.4264 maxiter = 1000 linear only rcane
uDmod2_rminer::fit_02 0.016 0.0405 0.0327 maxiter = 150 rminer
uDmod2_RSNNS::mlp_SCG_10 0.133 0.0562 0.0461 maxiter = 1000 RSNNS
uDmod2_simpleNeural::sN.MLPtrain_01 0.169 0.5547 0.4906 maxiter = 1000 for bi- or multiclass classification simpleNeural
uDmod2_snnR::snnR_01 0.023 0.2585 0.2264 maxiter = 200 better on multi snnR
uDmod2_softmaxreg::softmaxreg_01 0.000 0.5176 0.4253 maxiter = 1000 softmaxreg
uDmod2_tsensembler::tsensembler_01 0.078 0.0734 0.0557 maxiter = 150 uses nnet tsensembler
uDmod2_validann::ann_BFGS_08 0.588 0.0405 0.0327 maxiter = 200 optim validann

Dataset-uDreyfus1

event duration RMSE MAE stars params comment package
uDreyfus1_AMORE::train_ADAPTgdwm_01 0.385 0.0435 0.0347
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uDreyfus1_ANN2::neuralnetwork_adam_05 0.056 0.0172 0.0135
iter=4000 lr=0.02 Require fine tuning ANN2
uDreyfus1_brnn::brnn_gaussNewton_01 0.000 0.0301 0.0235 *** Different NN brnn
uDreyfus1_deepnet::gradientdescent_02 0.110 0.2631 0.2096 numepochs=1000 Bad on univariate datasets deepnet
uDreyfus1_h2o::h2o.deeplearning_05 0.578 0.2813 0.2409 maxiter=200 Bad on univariate datasets h2o
uDreyfus1_MachineShop::fit.NNetModel_03 0.000 0.0021 0.0017 maxiter = 150 uses nnet MachineShop
uDreyfus1_minpacklm::nlsLM_01 0.000 0.0000 0.0000 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uDreyfus1_momlp::monmlp.fit_BFGS_07 0.151 0.0019 0.0013 maxiter = 300 uses optimx momlp
uDreyfus1_neural::mlptrain_01 2.901 1.0568 0.9326 maxiter = 1000 classification neural
uDreyfus1_neuralnet::neuralnet_slr_04 0.094 0.0093 0.0081 neuralnet
uDreyfus1_nlsr::nlxb_01 0.032 0.0000 0.0000 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uDreyfus1_nnet::nnet_04 0.005 0.0020 0.0016 maxiter = 150 uses optim BFGS nnet
uDreyfus1_qrnn::qrnn.fit_03 0.144 0.0000 0.0000 maxiter = 700 qrnn
uDreyfus1_radiantmodel::radiantmodel_09 0.022 0.0044 0.0030 maxiter=10000 preset uses nnet radiantmodel
uDreyfus1_rcane::rlm_01 0.001 1.6305 1.2963 maxiter = 1000 linear only rcane
uDreyfus1_rminer::fit_01 0.009 0.0018 0.0015 maxiter = 150 rminer
uDreyfus1_RSNNS::mlp_Rprop_06 0.078 0.0619 0.0456 maxiter = 1000 RSNNS
uDreyfus1_simpleNeural::sN.MLPtrain_01 0.153 0.5027 0.3467 maxiter = 1000 for bi- or multiclass classification simpleNeural
uDreyfus1_snnR::snnR_01 0.010 0.3691 0.2756 maxiter = 200 better on multi snnR
uDreyfus1_softmaxreg::softmaxreg_01 0.000 1.6122 1.3725 maxiter = 1000 softmaxreg
uDreyfus1_tsensembler::tsensembler_04 0.058 0.1266 0.0850 maxiter = 150 uses nnet tsensembler
uDreyfus1_validann::ann_BFGS_09 0.149 0.0020 0.0016 maxiter = 200 optim validann

Dataset-uDreyfus2

event duration RMSE MAE stars params comment package
uDreyfus2_AMORE::train_ADAPTgdwm_08 0.384 0.1002 0.0792
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uDreyfus2_ANN2::neuralnetwork_adam_07 0.055 0.0981 0.0767
iter=4000 lr=0.02 Require fine tuning ANN2
uDreyfus2_brnn::brnn_gaussNewton_01 0.000 0.0971 0.0776 *** Different NN brnn
uDreyfus2_deepnet::gradientdescent_09 0.109 0.2790 0.2144 numepochs=1000 Bad on univariate datasets deepnet
uDreyfus2_h2o::h2o.deeplearning_10 0.501 0.2717 0.2102 maxiter=200 Bad on univariate datasets h2o
uDreyfus2_MachineShop::fit.NNetModel_03 0.006 0.0906 0.0725 maxiter = 150 uses nnet MachineShop
uDreyfus2_minpacklm::nlsLM_01 0.016 0.0906 0.0723 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uDreyfus2_momlp::monmlp.fit_BFGS_01 0.156 0.0910 0.0729 maxiter = 300 uses optimx momlp
uDreyfus2_neural::mlptrain_01 2.921 1.0574 0.9265 maxiter = 1000 classification neural
uDreyfus2_neuralnet::neuralnet_rprop-_03 0.093 0.0913 0.0720 Erratic on multivariate datasets neuralnet
uDreyfus2_nlsr::nlxb_01 0.062 0.0906 0.0723 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uDreyfus2_nnet::nnet_06 0.005 0.0906 0.0724 maxiter = 150 uses optim BFGS nnet
uDreyfus2_qrnn::qrnn.fit_03 0.191 0.0956 0.0684 maxiter = 700 qrnn
uDreyfus2_radiantmodel::radiantmodel_02 0.023 0.0906 0.0723 maxiter=10000 preset uses nnet radiantmodel
uDreyfus2_rcane::rlm_01 0.000 1.6298 1.2982 maxiter = 1000 linear only rcane
uDreyfus2_rminer::fit_02 0.015 0.0906 0.0724 maxiter = 150 rminer
uDreyfus2_RSNNS::mlp_Rprop_04 0.078 0.1122 0.0886 maxiter = 1000 RSNNS
uDreyfus2_simpleNeural::sN.MLPtrain_01 0.154 0.4931 0.3545 maxiter = 1000 for bi- or multiclass classification simpleNeural
uDreyfus2_snnR::snnR_01 0.010 0.3837 0.2773 maxiter = 200 better on multi snnR
uDreyfus2_softmaxreg::softmaxreg_01 0.000 1.6087 1.3690 maxiter = 1000 softmaxreg
uDreyfus2_tsensembler::tsensembler_09 0.072 0.1530 0.1109 maxiter = 150 uses nnet tsensembler
uDreyfus2_validann::ann_BFGS_01 0.232 0.0906 0.0724 maxiter = 200 optim validann

Dataset-uGauss1

event duration RMSE MAE stars params comment package
uGauss1_AMORE::train_ADAPTgdwm_08 1.156 2.3558 1.8756
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uGauss1_ANN2::neuralnetwork_adam_03 0.467 2.3603 1.8819
iter=4000 lr=0.02 Require fine tuning ANN2
uGauss1_brnn::brnn_gaussNewton_03 0.047 2.2447 1.7473 *** Different NN brnn
uGauss1_deepnet::gradientdescent_09 0.391 6.0340 4.8565 numepochs=1000 Bad on univariate datasets deepnet
uGauss1_h2o::h2o.deeplearning_07 0.516 9.5879 7.8046 maxiter=200 Bad on univariate datasets h2o
uGauss1_MachineShop::fit.NNetModel_07 0.016 2.2456 1.7438 maxiter = 150 uses nnet MachineShop
uGauss1_minpacklm::nlsLM_07 0.078 2.2282 1.7250 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uGauss1_momlp::monmlp.fit_BFGS_09 0.185 2.3281 1.8434 maxiter = 300 uses optimx momlp
uGauss1_neural::mlptrain_01 21.022 31.5754 27.2849 maxiter = 1000 classification neural
uGauss1_neuralnet::neuralnet_rprop+_01 2.129 2.2509 1.7664 Erratic on difficult datasets neuralnet
uGauss1_nlsr::nlxb_02 0.172 2.2333 1.7391 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uGauss1_nnet::nnet_09 0.060 2.2384 1.7372 maxiter = 150 uses optim BFGS nnet
uGauss1_qrnn::qrnn.fit_08 0.287 2.2468 1.7022 maxiter = 700 qrnn
uGauss1_radiantmodel::radiantmodel_05 0.093 2.2289 1.7264 maxiter=10000 preset uses nnet radiantmodel
uGauss1_rcane::rlm_01 0.000 73.4624 60.5314 maxiter = 1000 linear only rcane
uGauss1_rminer::fit_07 0.068 2.2347 1.7381 maxiter = 150 rminer
uGauss1_RSNNS::mlp_BackpropChunk_02 0.310 2.7267 2.1229 maxiter = 1000 RSNNS
uGauss1_simpleNeural::sN.MLPtrain_01 0.492 0.4805 0.3934 maxiter = 1000 for bi- or multiclass classification simpleNeural
uGauss1_snnR::snnR_05 0.057 6.1846 5.1406 maxiter = 200 better on multi snnR
uGauss1_softmaxreg::softmaxreg_01 0.000 41.6253 36.1679 maxiter = 1000 softmaxreg
uGauss1_tsensembler::tsensembler_09 0.479 2.7080 2.1559 maxiter = 150 uses nnet tsensembler
uGauss1_validann::ann_BFGS_01 0.781 2.2356 1.7373 maxiter = 200 optim validann

Dataset-uGauss2

event duration RMSE MAE stars params comment package
uGauss2_AMORE::train_ADAPTgdwm_08 0.969 2.9516 2.3865
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uGauss2_ANN2::neuralnetwork_adam_01 0.419 2.5416 2.0158
iter=4000 lr=0.02 Require fine tuning ANN2
uGauss2_brnn::brnn_gaussNewton_01 0.047 2.3530 1.8475 *** Different NN brnn
uGauss2_deepnet::gradientdescent_08 0.359 6.7735 4.8847 numepochs=1000 Bad on univariate datasets deepnet
uGauss2_h2o::h2o.deeplearning_06 0.547 6.9879 5.0515 maxiter=200 Bad on univariate datasets h2o
uGauss2_MachineShop::fit.NNetModel_05 0.016 2.4067 1.8987 maxiter = 150 uses nnet MachineShop
uGauss2_minpacklm::nlsLM_04 0.062 2.3326 1.8306 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uGauss2_momlp::monmlp.fit_BFGS_02 0.191 2.9003 2.3193 maxiter = 300 uses optimx momlp
uGauss2_neural::mlptrain_05 17.569 28.8083 20.0674 maxiter = 1000 classification neural
uGauss2_neuralnet::neuralnet_rprop+_05 9.622 2.4326 1.9185 Erratic on difficult datasets neuralnet
uGauss2_nlsr::nlxb_09 0.109 2.3386 1.8372 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uGauss2_nnet::nnet_08 0.011 2.3888 1.8810 maxiter = 150 uses optim BFGS nnet
uGauss2_qrnn::qrnn.fit_10 0.299 2.3480 1.8193 maxiter = 700 qrnn
uGauss2_radiantmodel::radiantmodel_08 0.122 2.3410 1.8370 maxiter=10000 preset uses nnet radiantmodel
uGauss2_rcane::rlm_01 0.000 71.3049 60.5319 maxiter = 1000 linear only rcane
uGauss2_rminer::fit_03 0.065 2.3806 1.8779 maxiter = 150 rminer
uGauss2_RSNNS::mlp_Std_Backpropagation_01 0.298 3.3022 2.5900 maxiter = 1000 RSNNS
uGauss2_simpleNeural::sN.MLPtrain_01 0.428 0.5300 0.4474 maxiter = 1000 for bi- or multiclass classification simpleNeural
uGauss2_snnR::snnR_05 0.042 8.8419 6.4413 maxiter = 200 better on multi snnR
uGauss2_softmaxreg::softmaxreg_01 0.002 37.6867 31.6105 maxiter = 1000 softmaxreg
uGauss2_tsensembler::tsensembler_07 0.527 2.3730 1.8654 maxiter = 150 uses nnet tsensembler
uGauss2_validann::ann_BFGS_05 0.581 2.3529 1.8492 maxiter = 200 optim validann

Dataset-uGauss3

event duration RMSE MAE stars params comment package
uGauss3_AMORE::train_ADAPTgdwm_04 0.969 2.4105 1.9502
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uGauss3_ANN2::neuralnetwork_adam_02 0.424 2.3393 1.8581
iter=4000 lr=0.02 Require fine tuning ANN2
uGauss3_brnn::brnn_gaussNewton_05 0.047 2.3307 1.8502 *** Different NN brnn
uGauss3_deepnet::gradientdescent_07 0.375 4.1246 3.2762 numepochs=1000 Bad on univariate datasets deepnet
uGauss3_h2o::h2o.deeplearning_06 0.609 4.1699 3.2997 maxiter=200 Bad on univariate datasets h2o
uGauss3_MachineShop::fit.NNetModel_03 0.023 2.2937 1.8248 maxiter = 150 uses nnet MachineShop
uGauss3_minpacklm::nlsLM_06 0.063 2.2770 1.8053 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uGauss3_momlp::monmlp.fit_BFGS_07 0.178 2.3234 1.8745 maxiter = 300 uses optimx momlp
uGauss3_neural::mlptrain_05 17.522 29.4381 21.0784 maxiter = 1000 classification neural
uGauss3_neuralnet::neuralnet_rprop+_05 0.500 2.3338 1.8754 Erratic on difficult datasets neuralnet
uGauss3_nlsr::nlxb_10 0.094 2.2998 1.8387 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uGauss3_nnet::nnet_06 0.038 2.2928 1.8257 maxiter = 150 uses optim BFGS nnet
uGauss3_qrnn::qrnn.fit_02 0.266 2.3738 1.8047 maxiter = 700 qrnn
uGauss3_radiantmodel::radiantmodel_01 0.262 2.7950 2.1974 maxiter=10000 preset uses nnet radiantmodel
uGauss3_rcane::rlm_01 0.000 72.5907 60.5319 maxiter = 1000 linear only rcane
uGauss3_rminer::fit_08 0.057 2.2933 1.8251 maxiter = 150 rminer
uGauss3_RSNNS::mlp_BackpropMomentum_01 0.305 2.7896 2.2194 maxiter = 1000 RSNNS
uGauss3_simpleNeural::sN.MLPtrain_01 0.466 0.5346 0.4431 maxiter = 1000 for bi- or multiclass classification simpleNeural
uGauss3_snnR::snnR_01 0.035 5.2818 4.0957 maxiter = 200 better on multi snnR
uGauss3_softmaxreg::softmaxreg_01 0.000 40.0663 34.1007 maxiter = 1000 softmaxreg
uGauss3_tsensembler::tsensembler_01 0.451 2.6345 2.1087 maxiter = 150 uses nnet tsensembler
uGauss3_validann::ann_BFGS_05 0.608 2.2859 1.8130 maxiter = 200 optim validann

Dataset-uNeuroOne

event duration RMSE MAE stars params comment package
uNeuroOne_AMORE::train_ADAPTgdwm_01 0.329 0.2831 0.2305
iter=10000 lr=0.009 momentum=0.8 sigmoid AMORE
uNeuroOne_ANN2::neuralnetwork_rmsprop_08 0.062 0.2834 0.2327 iter=4000 lr=0.03 Erratic ANN2
uNeuroOne_brnn::brnn_gaussNewton_05 0.000 0.3585 0.2925 *** Different NN brnn
uNeuroOne_deepnet::gradientdescent_03 0.109 0.2845 0.2330 numepochs=1000 Bad on univariate datasets deepnet
uNeuroOne_h2o::h2o.deeplearning_10 0.562 0.2935 0.2447 maxiter=200 Bad on univariate datasets h2o
uNeuroOne_MachineShop::fit.NNetModel_01 0.004 0.2830 0.2313 maxiter = 150 uses nnet MachineShop
uNeuroOne_minpacklm::nlsLM_01 0.000 0.2830 0.2313 ** maxiter = 150 Require hand-made formulas and scaling minpacklm
uNeuroOne_momlp::monmlp.fit_BFGS_01 0.161 0.2830 0.2312 maxiter = 300 uses optimx momlp
uNeuroOne_neural::mlptrain_03 2.207 0.9593 0.6626 maxiter = 1000 classification neural
uNeuroOne_neuralnet::neuralnet_rprop+_03 0.031 0.2830 0.2315 Erratic on difficult datasets neuralnet
uNeuroOne_nlsr::nlxb_01 0.015 0.2830 0.2313 ** maxiter = 150 Require hand-made formulas and scaling nlsr
uNeuroOne_nnet::nnet_01 0.000 0.2830 0.2313 maxiter = 150 uses optim BFGS nnet
uNeuroOne_qrnn::qrnn.fit_01 0.047 0.2939 0.2258 maxiter = 700 qrnn
uNeuroOne_radiantmodel::radiantmodel_01 0.016 0.2830 0.2313 maxiter=10000 preset uses nnet radiantmodel
uNeuroOne_rcane::rlm_01 0.000 1.3012 1.1081 maxiter = 1000 linear only rcane
uNeuroOne_rminer::fit_01 0.016 0.2830 0.2313 maxiter = 150 rminer
uNeuroOne_RSNNS::mlp_Rprop_04 0.063 0.2830 0.2313 maxiter = 1000 RSNNS
uNeuroOne_simpleNeural::sN.MLPtrain_01 0.148 0.6469 0.5772 maxiter = 1000 for bi- or multiclass classification simpleNeural
uNeuroOne_snnR::snnR_01 0.007 0.6793 0.5564 maxiter = 200 better on multi snnR
uNeuroOne_softmaxreg::softmaxreg_01 0.000 1.2720 1.1104 maxiter = 1000 softmaxreg
uNeuroOne_tsensembler::tsensembler_01 0.064 0.2866 0.2356 maxiter = 150 uses nnet tsensembler
uNeuroOne_validann::ann_BFGS_01 0.084 0.2830 0.2313 maxiter = 200 optim validann