Fit WGAN_GP on a training dataset. Parameters ---------- X_real : :py:class:`ndarray <numpy.ndarray>` of shape `(n_e

Fit the VAE to a training dataset. Parameters ---------- X_train : :py:class:`ndarray <numpy.ndarray>` of shape `(n_

Build a ball tree recursively using the O(M log N) `k`-d construction algorithm. Notes ----- Recursively div

Given an observation sequence `O` and the set of possible latent states, learn the MLE HMM parameters `A` and `B`. Notes

Create mappings between columns and category labels. Parameters ---------- categories : list of length `C`

Store the feature-wise mean and standard deviation across the samples in `X` for future scaling. Parameters --------

Build a Huffman tree for the tokens in `text` and compute each token's binary encoding. Notes ----- In a Huf

Compute term-frequencies and inverse document frequencies on a collection of documents. Parameters ----------

Factor a data matrix into two low rank factors via ALS. Parameters ---------- X : numpy array of shape `(N, M)`

Fit the regression coefficients via gradient descent on the negative log likelihood. Parameters ---------- X

Fit the regression coefficients via maximum likelihood. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>

Find the maximum likelihood GLM coefficients via IRLS. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>`

Fit the model parameters via maximum likelihood. Notes ----- The model parameters are stored in the :py:attr:`parame

Estimate `phi`, the word-topic distribution, and `theta`, the topic-document distribution. Parameters ----------

Set a fixed aspect ratio on matplotlib plots regardless of axis units

Erase all the wrapper and base layer's derived variables and gradients.

Erase all the layer's derived variables and gradients.

Erase all the layer's derived variables and gradients.

Reset parameter gradients after update

Reset parameter gradients after update

Erase all the layer's derived variables and gradients.

Apply the activation function to an input

r""" Evaluate the leaky ReLU function on the elements of input `z`. .. math:: \text{LeakyReLU}(z_i) &=

Compute the tanh function on the elements of input `z`.

r""" Evaluate the SELU activation on the elements of input `z`. .. math:: \text{SELU}(z_i) = \text{scale} \times \text

Compute the module output on a single minibatch. Parameters ---------- X_main : :py:class:`ndarray <numpy.ndarray>`

Compute the module output given input volume `X`. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of s

Compute the layer output given input volume `X`. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sh

Run a forward pass across all timesteps in the input. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>`

r""" Compute the attention-weighted output of a collection of keys, values, and queries. Notes ----- In the m

r""" Compute the layer output on a single minibatch. Parameters ---------- X : list of length `n_inputs`

r""" Compute the layer output on a single minibatch. Parameters ---------- X : list of length `n_inputs`

Compute the layer output on a single minibatch. Notes ----- Equations [train]:: Y = scaler * norm(X) +

Compute the layer output on a single minibatch. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sha

Compute the layer output on a single minibatch. Notes ----- Equations [train & test]:: Y = scaler * nor

Compute the layer output on a single minibatch. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sha

Compute the layer output on a single minibatch. Notes ----- Equations: Y = W[x] Parameters

Compute the layer output on a single minibatch. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sha

Compute the layer output given input volume `X`. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sh

Compute the layer output given input volume `X`. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sh

Compute the layer output given input volume `X`. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of sh

Compute the network output for a single timestep. Parameters ---------- Xt : :py:class:`ndarray <numpy.ndarray>` of

Compute the layer output for a single timestep. Parameters ---------- Xt : :py:class:`ndarray <numpy.ndarray>` of sh

VAE forward pass

Evaluate the network on a single minibatch. Parameters ---------- X : :py:class:`ndarray <numpy.ndarray>` of shape `

Freeze the base layer's parameters at their current values so they can no longer be updated.

Compute the probability that a random draw from a 1D Gaussian with mean `mean` and variance `var` is less than or equal to `x`.

Sample a sequence from the HMM. Parameters ---------- n_steps : int The length of the generated sequence

Sample the context vectors for each arm from a multivariate standard normal distribution. Returns ------- co

r""" Evaluate the first derivative of the leaky ReLU function on the elements of input `x`. .. math:: \frac{\par

r""" Evaluate the first derivative of the SELU activation on the elements of input `x`. .. math:: \frac{\partial

Gradient of the squared error loss with respect to the pre-nonlinearity input, `z`. Notes ----- The current

Compute the gradient of the cross entropy loss with regard to the softmax input, `z`. Notes ----- The gradie

Compute the Hamming distance between two integer-valued vectors. Notes ----- The Hamming distance between two vectors **x** and **y*

Initialize scheduler from the param dictionary

Initialize optimizer from the `param` dictonary

Initialize activation function from the `param` string

Initialize scheduler from the param string

Initialize optimizer from the `param` string

Initialize the layer wrappers in `wrapper_list` and return a wrapped `layer` object. Parameters ---------- layer : :doc:`Layer <

Provide reasonable initializations for model and variational parameters.