Stacked Deep Autoencoding System

From GM-RKB
Jump to navigation Jump to search

A Stacked Deep Autoencoding System is a autoencoder training system that implements a stacked deep autoencoding algorithm to solve a ...



References

2016

  • http://deep-learning-tensorflow.readthedocs.io/en/latest/#stacked-deep-autoencoder
    • QUOTE: Stacked Deep Autoencoder

      Stack of Denoising Autoencoders used to build a Deep Network for unsupervised learning.

      Cmd example usage::

      • python command_line/run_stacked_autoencoder_unsupervised.py --dae_layers 512,256,128 --dae_batch_size 25 --dae_num_epochs 5 --verbose 1 --dae_corr_type masking --dae_corr_frac 0.0 --finetune_num_epochs 25 --finetune_batch_size 32 --finetune_opt gradient_descent --finetune_learning_rate 0.05 --dae_enc_act_func sigmoid --dae_dec_act_func sigmoid --dae_loss_func cross_entropy --finetune_enc_act_func tanh --finetune_dec_act_func sigmoid --finetune_loss_func cross_entropy --dropout 0.7