pydbm.dbm.restrictedboltzmannmachines package

Submodules

pydbm.dbm.restrictedboltzmannmachines.rt_rbm module

class pydbm.dbm.restrictedboltzmannmachines.rt_rbm.RTRBM

Bases: pydbm.dbm.restricted_boltzmann_machines.RestrictedBoltzmannMachine

Reccurent temploral restricted boltzmann machine.

get_feature_points

Extract feature points from hidden layer.

Returns:np.ndarray of feature points.
get_reconstruct_error_arr

Extract reconstructed errors.

Retruns:
np.ndarray of reconstructed errors.
get_reconstructed_arr

Extract reconstructed points.

Returns:np.ndarray of reconstructed points.
inference

Inferencing.

Parameters:
  • observed_data_arr – The np.ndarray of observed data points, which is a rank-3 array-like or sparse matrix of shape: (The number of samples, The length of cycle, The number of features)
  • r_batch_size

    Batch size. If this value is 0, the inferencing is a recursive learning. If this value is more than 0, the inferencing is a mini-batch recursive learning. If this value is ‘-1’, the inferencing is not a recursive learning.

    If you do not want to execute the mini-batch training, the value of batch_size must be -1. And r_batch_size is also parameter to control the mini-batch training but is refered only in inference and reconstruction. If this value is more than 0, the inferencing is a kind of reccursive learning with the mini-batch training.

  • batch_size – Batch size in learning.
Returns:

The np.ndarray of feature points.

learn

Learning.

Parameters:
  • observed_data_arr – The np.ndarray of observed data points, which is a rank-3 array-like or sparse matrix of shape: (The number of samples, The length of cycle, The number of features)
  • traning_count – Training counts.
  • batch_size – Batch size.

Module contents