Demonstrates how to train and test a stochastic denoising autoencoder. This is demonstrated on MNIST. :type learning_rate: float :p

This demo is tested on MNIST :type learning_rate: float :param learning_rate: learning rate used for training the contracting

This demo is tested on MNIST :type learning_rate: float :param learning_rate: learning rate used for training the DeNosing

Demonstrate stochastic gradient descent optimization for a multilayer perceptron This is demonstrated on MNIST. :type learning_rate

Demonstrate how to train and afterwards sample from it using Theano. This is demonstrated on MNIST. :param learning_rate: learning rate

Train the RNN-RBM via stochastic gradient descent (SGD) using MIDI files converted to piano-rolls. files : list of strings

When we reload the model. Needed for the GPU stuff.

Initialize the dA2 class by specifying the number of visible units (the dimension d of the input ), the number of hidden units ( the

Constructs and compiles Theano functions for training and sequence generation. n_hidden : integer Number of hidden units

RBM constructor. Defines the parameters of the model along with basic operations for inferring hidden from visible (and vice-versa),

Initialize the dA class by specifying the number of visible units (the dimension d of the input ), the number of hidden units ( the d

This class is made to support a variable number of layers. :type numpy_rng: numpy.random.RandomState :param numpy_rng: numpy random n

This class is made to support a variable number of layers. :type numpy_rng: numpy.random.RandomState :param numpy_rng: numpy random

Initialize the cA class by specifying the number of visible units (the dimension d of the input), the number of hidden units (the dime

Allocate a LeNetConvPoolLayer with shared variable internal parameters. :type rng: numpy.random.RandomState :param rng: a ra

Typical hidden layer of a MLP: units are fully-connected and have sigmoidal activation function. Weight matrix W is of shape (n_in,n_

Initialize the parameters for the multilayer perceptron :type rng: numpy.random.RandomState :param rng: a random number generator use

nh :: dimension of the hidden layer nc :: number of classes ne :: number of word embeddings in the vocabulary de :: d

Initialize the parameters of the logistic regression :type input: theano.tensor.TensorType :param input: symbolic variable that desc

Initialize the parameters of the logistic regression :type input: theano.tensor.TensorType :param input: symbolic variable that desc

An adaptive learning rate optimizer Parameters ---------- lr : Theano SharedVariable Initial learning rate tpramas: Thea

Returns tuple containing dictionary of calling function's named arguments and a list of calling function's unnamed positional arguments.

Function to perform Entropy-Minimization-Clustering.

Function to perform Maximal-Margin-Clustering.

Implement dropout

This function computes the cost and the updates .

This function computes the cost and the updates.

Computes the values of the hidden layer Removed the nonlinearity

Computes the reconstructed input given the values of the hidden layer

This function implements one step of Gibbs sampling, starting from the hidden state

This function implements one step of Gibbs sampling, starting from the visible state

Inside loop of Scan. Performs one step of leapfrog update, using Hamiltonian dynamics. Parameters ----------

Load the dataset, perform shuffling

:param shared_positions: theano ndarray shared var with many particle [initial] positions :param energy_fn:

Init the LSTM parameter: :see: init_params

If you want to use a trained model, this is useful to compute the probabilities of new examples.

An example of how to load a trained model and use it to predict labels.

A variant of SGD that scales the step size by running average of the recent step norms. Parameters ---------- lr : Theano Share

Stochastic Gradient Descent :note: A more complicated version of sgd then needed. This is done like that for adadelta and rmsprop.

This fonction modify the configuration theano and don't restore it!