Use CD-1 training procedure, basically an exact inference for `positive_associations`, followed by a "non burn-in" block Gibbs Sampling for th

Generate binary addition dataset. http://devankuleindiren.com/Projects/rnn_arithmetic.php

Approximate leaf value.

Calculate an error for given examples.

Returns loss function by the name.

Plot contour for 2D data.

Calculate output shape for pooling layer.

Allocates initial weights.

Returns shape of the current layer.

Shuffle rows in the dataset.

Smooth relu.

Transform predictions values.

A t-Distributed Stochastic Neighbor Embedding implementation. Parameters ---------- max_iter : int, default 200 perpl

Principal component analysis (PCA) implementation. Transforms a dataset of possibly correlated values into n linearly uncorrelated co

Basic class for implementing continuous regression estimators which are trained with gradient descent optimization on their particular loss

Simplified factorization machines implementation using SGD optimizer.

Bernoulli Restricted Boltzmann Machine (RBM) Parameters ---------- n_hidden : int, default 128 The number of hid

Base class for Nearest neighbors classifier and regressor. Parameters ---------- k : int, default 5 The number of

A container for layer's parameters. Parameters ---------- init : str, default 'glorot_uniform'. The name of the w

A fully connected layer. Parameters ---------- output_dim : int

A 2D convolutional layer. Input shape: (n_images, n_channels, height, width) Parameters ---------- n_filters : int, d

Max pooling layer. Input shape: (n_images, n_channels, height, width) Parameters ---------- pool_shape : tuple(int, i

Deep Q learning implementation. Parameters ---------- min_epsilon : float Minimal value for epsilon. eps