Raw File
Tip revision: d34ca22544dff11d21f1b644da9853880a50f9c4 authored by Alex Boulangé on 23 November 2018, 17:30:03 UTC
version 1.2.0
Tip revision: d34ca22
automl 1.2.0
* New param 'mdlref' for automl_train_manual:
  to start training from saved model (shape,
  weights...) for fine tuning
* New param 'mdlref' for automl_train:
  to start training with loaded hpar and autopar
  (not the model)
* New 'auto_runtype' autopar for automl_train
  to run automatically the 2 steps below;
  1: overfitting, goal: performance
  2: regularization, goal: generalization
* dropout bug fix
* lambda bug fix

automl 1.1.0
* same train/test sampling for each particle with automl_train
* stick to a format in variables naming

automl 1.0.9
* testcvsize = 0 bug fix

automl 1.0.8
* New automatic hyperparameters adjustments below:
  'auto_psovelocitymaxratio' autopar PSO velocity max ratio
  'auto_layer' autopar layer shape (layers number, nodes
  number per layer, activation types and dropout ratios)
* 'auto_lambda' bug fix

automl 1.0.7
* vignette completion

automl 1.0.6
* vignette howto_automl: why, how and basic howto
* 'auto_lambda' autopar regularization hyperparameter
* seed bug fix for reproductibility
* display enhancement in NN structure display

automl 1.0.5
* first public release on CRAN
* There's so much to do; transfert learning, CNN, RNN ...
  feel free to join
back to top