Welcome to pydbm’s documentation!

Contents:

• Deep Learning Library: pydbm
  • Documentation
  • Installation
    • Source code
    • Python package index(PyPI)
    • Dependencies
      • Options
  • Description
    • The structure of RBM.
    • The learning equations of RBM.
    • Contrastive Divergence as an approximation method.
    • The structure of DBM.
    • DBM as a Stacked Auto-Encoder.
    • Structural expansion for RTRBM.
    • Structural expansion for RNN-RBM.
    • Structural expansion for LSTM-RTRBM.
      • Structure of LSTM.
      • Structure of LSTM-RTRBM.
    • Structural expansion for Shape-BM.
    • The Commonality/Variability Analysis in order to practice object-oriented design.
    • Functionally equivalent: Encoder/Decoder based on LSTM.
      • Encoder/Decoder for Anomaly Detection(EncDec-AD)
    • Functionally equivalent: Convolutional Auto-Encoder.
    • Structural expansion for Convolutional LSTM(ConvLSTM).
    • Structural expansion for Spatio-Temporal Auto-Encoder.
      • Video recognition and reconstruction of video images.
    • Structural extension from Auto-Encoders and Encoder/Decoders to energy-based models and Generative models.
    • Composition and Correspondence in this library
  • Usecase: Building the Deep Boltzmann Machine for feature extracting.
  • Usecase: Extracting all feature points for dimensions reduction(or pre-learning)
    • Extract reconstruction error rate.
    • Extract the result of dimention reduction
    • Extract weights obtained by pre-learning.
    • Extract biases obtained by pre-learning.
    • Save pre-learned parameters.
    • Transfer learning in DBM.
    • Performance
      • Detail
  • Usecase: Building the RTRBM for recursive learning.
    • Learning.
    • Inferencing.
    • Feature points.
    • Reconstructed data.
    • Save pre-learned parameters.
    • Transfer learning in RTRBM.
  • Usecase: Building the RNN-RBM for recursive learning.
  • Usecase: Building the LSTM-RTRBM for recursive learning.
  • Usecase: Image segmentation by Shape-BM.
    • Save pre-learned parameters and transfer learning in Shape Boltzmann Machine.
  • Usecase: Casual use by facade for building Encoder/Decoder based on LSTM.
    • Save pre-learned parameters.
    • Transfer learning in Encoder/Decoder based on LSTM.
    • For more detail settings.
  • Usecase: Build Encoder/Decoder based on LSTM or ConvLSTM as a reconstruction model.
  • Usecase: Build Convolutional Auto-Encoder.
    • Save pre-learned parameters.
    • Transfer learning in Convolutional Auto-Encoder.
  • Usecase: Build Spatio-Temporal Auto-Encoder.
    • Save pre-learned parameters.
      • Naming rule of saved files.
    • Transfer learning in Spatio-Temporal Auto-Encoder.
  • Usecase: Build Optimizer.
    • Adaptive subgradient methods(AdaGrad).
    • Adaptive RootMean-Square (RMSProp) gradient decent algorithm.
    • Nesterov’s Accelerated Gradient(NAG).
    • Adaptive Moment Estimation(Adam).
    • Nesterov-accelerated Adaptive Moment Estimation(Nadam).
  • Usecase: Tied-weights.
  • Usecase: Build and delegate image generator.
  • Usecase: Save and load the pre-learned parameters in computation graphs.
  • References
    • Deep Boltzmann machines.
    • Encoder/Decoder schemes with an Attention mechanism.
    • Auto-Encoders.
    • Generative Adversarial Networks(GANs).
    • Unsupervised / Supervised pre-training
    • Representations learning.
    • Semi-supervised learning.
    • Deep Embedded Clustering.
    • Optimizations.
    • Algorithms, Arithmetic, and Regularizations
    • Related PoC
    • More detail demos
  • Author
  • Author URI
  • License
• pydbm package
  • Subpackages
    • pydbm.activation package
      • Subpackages
      • Submodules
      • pydbm.activation.identity_function module
      • pydbm.activation.logistic_function module
      • pydbm.activation.relu_function module
      • pydbm.activation.sign_function module
      • pydbm.activation.softmax_function module
      • pydbm.activation.tanh_function module
      • Module contents
    • pydbm.approximation package
      • Subpackages
      • Submodules
      • pydbm.approximation.contrastive_divergence module
      • pydbm.approximation.rt_rbm_cd module
      • pydbm.approximation.shape_bm_cd module
      • Module contents
    • pydbm.clustering package
      • Subpackages
      • Submodules
      • pydbm.clustering.deep_embedded_clustering module
      • pydbm.clustering.reconstruction_classification_networks module
      • pydbm.clustering.sklearn_kmeans module
      • Module contents
    • pydbm.cnn package
      • Subpackages
      • Submodules
      • pydbm.cnn.convolutional_neural_network module
      • pydbm.cnn.feature_generator module
      • pydbm.cnn.layerable_cnn module
      • pydbm.cnn.spatio_temporal_auto_encoder module
      • Module contents
    • pydbm.dbm package
      • Subpackages
      • Submodules
      • pydbm.dbm.dbm_director module
      • pydbm.dbm.deep_boltzmann_machine module
      • pydbm.dbm.recurrent_temporal_rbm module
      • pydbm.dbm.restricted_boltzmann_machines module
      • pydbm.dbm.rtrbm_director module
      • Module contents
    • pydbm.loss package
      • Subpackages
      • Submodules
      • pydbm.loss.cross_entropy module
      • pydbm.loss.kl_divergence module
      • pydbm.loss.mean_squared_error module
      • Module contents
    • pydbm.nn package
      • Subpackages
      • Submodules
      • pydbm.nn.neural_network module
      • pydbm.nn.nn_layer module
      • pydbm.nn.simple_auto_encoder module
      • Module contents
    • pydbm.optimization package
      • Subpackages
      • Submodules
      • pydbm.optimization.batch_norm module
      • pydbm.optimization.opt_params module
      • Module contents
    • pydbm.rnn package
      • Subpackages
      • Submodules
      • pydbm.rnn.encoder_decoder_controller module
      • pydbm.rnn.facade_attention_encoder_decoder module
      • pydbm.rnn.facade_encoder_decoder module
      • pydbm.rnn.lstm_model module
      • Module contents
    • pydbm.synapse package
      • Subpackages
      • Submodules
      • pydbm.synapse.cnn_graph module
      • pydbm.synapse.cnn_output_graph module
      • pydbm.synapse.complete_bipartite_graph module
      • pydbm.synapse.nn_graph module
      • pydbm.synapse.recurrent_temporal_graph module
      • Module contents
    • pydbm.verification package
      • Subpackages
      • Submodules
      • pydbm.verification.verificate_function_approximation module
      • pydbm.verification.verificate_softmax module
      • Module contents
  • Submodules
  • pydbm.params_initializer module
  • pydbm.synapse_list module
  • Module contents

Indices and tables

• Index
• Module Index
• Search Page