ReferenceΒΆ
This package groups together a bunch of Theano code for neural nets.
theanets.activations.Activation (name, layer, ...) |
An activation function for a neural network layer. |
theanets.activations.LGrelu (*args, **kwargs) |
Rectified linear activation with learnable leak rate and gain. |
theanets.activations.Maxout (*args, **kwargs) |
Arbitrary piecewise linear activation. |
theanets.activations.Prelu (*args, **kwargs) |
Parametric rectified linear activation with learnable leak rate. |
theanets.activations.build (name, layer, **kwargs) |
Construct an activation function by name. |
theanets.feedforward.Autoencoder (layers[, ...]) |
An autoencoder network attempts to reproduce its input. |
theanets.feedforward.Classifier (layers[, ...]) |
A classifier computes a distribution over labels, given an input. |
theanets.feedforward.Regressor ([layers, ...]) |
A regressor attempts to produce a target output given some inputs. |
theanets.graph.Network ([layers, loss, weighted]) |
The network class encapsulates a network computation graph. |
theanets.layers.base.Concatenate (size, inputs) |
Concatenate multiple inputs along the last axis. |
theanets.layers.base.Flatten (size, inputs[, ...]) |
Flatten all but the batch index of the input. |
theanets.layers.base.Input (size[, name, ...]) |
A layer that receives external input data. |
theanets.layers.base.Layer (size, inputs[, ...]) |
Base class for network layers. |
theanets.layers.base.Product (size, inputs[, ...]) |
Multiply several inputs together elementwise. |
theanets.layers.base.Reshape (shape, **kwargs) |
Reshape an input to have different numbers of dimensions. |
theanets.layers.convolution.Conv1 (filter_size) |
1-dimensional convolutions run over one data axis. |
theanets.layers.feedforward.Classifier (**kwargs) |
A classifier layer performs a softmax over a linear input transform. |
theanets.layers.feedforward.Feedforward (...) |
A feedforward neural network layer performs a transform of its input. |
theanets.layers.feedforward.Tied (partner, ...) |
A tied-weights feedforward layer shadows weights from another layer. |
theanets.layers.recurrent.ARRNN (size, inputs) |
An RNN with adaptive rate per unit. |
theanets.layers.recurrent.Bidirectional ([worker]) |
A bidirectional recurrent layer runs worker models forward and backward. |
theanets.layers.recurrent.Clockwork (periods, ...) |
A Clockwork RNN layer updates “modules” of neurons at specific rates. |
theanets.layers.recurrent.GRU (size, inputs) |
Gated Recurrent Unit layer. |
theanets.layers.recurrent.LRRNN (size, inputs) |
An RNN with learned rate for each unit. |
theanets.layers.recurrent.LSTM (size, inputs) |
Long Short-Term Memory (LSTM) layer. |
theanets.layers.recurrent.MRNN ([factors]) |
A recurrent network layer with multiplicative dynamics. |
theanets.layers.recurrent.MUT1 (size, inputs) |
“MUT1” evolved recurrent layer. |
theanets.layers.recurrent.RNN (size, inputs) |
Standard recurrent network layer. |
theanets.losses.CrossEntropy (target[, ...]) |
Cross-entropy (XE) loss function for classifiers. |
theanets.losses.GaussianLogLikelihood ([...]) |
Gaussian Log Likelihood (GLL) loss function. |
theanets.losses.Hinge (target[, weight, ...]) |
Hinge loss function for classifiers. |
theanets.losses.KullbackLeiblerDivergence (target) |
The KL divergence loss is computed over probability distributions. |
theanets.losses.Loss (target[, weight, ...]) |
A loss function base class. |
theanets.losses.MaximumMeanDiscrepancy ([kernel]) |
Maximum Mean Discrepancy (MMD) loss function. |
theanets.losses.MeanAbsoluteError (target[, ...]) |
Mean-absolute-error (MAE) loss function. |
theanets.losses.MeanSquaredError (target[, ...]) |
Mean-squared-error (MSE) loss function. |
theanets.recurrent.Autoencoder (layers[, ...]) |
An autoencoder network attempts to reproduce its input. |
theanets.recurrent.Classifier (layers[, ...]) |
A classifier computes a distribution over labels, given an input. |
theanets.recurrent.Regressor ([layers, loss, ...]) |
A regressor attempts to produce a target output given some inputs. |
theanets.recurrent.Text (text[, alpha, ...]) |
A class for handling sequential text data. |
theanets.recurrent.batches (arrays[, steps, ...]) |
Create a callable that generates samples from a dataset. |
theanets.regularizers.BernoulliDropout ([...]) |
Randomly set activations of a layer output to zero. |
theanets.regularizers.Contractive ([pattern, ...]) |
Penalize the derivative of hidden layers with respect to their inputs. |
theanets.regularizers.GaussianNoise ([...]) |
Add isotropic Gaussian noise to one or more graph outputs. |
theanets.regularizers.HiddenL1 ([pattern, weight]) |
Penalize the activation of hidden layers under an L1 norm. |
theanets.regularizers.Regularizer ([pattern, ...]) |
A regularizer for a neural network model. |
theanets.regularizers.WeightL1 ([pattern, weight]) |
Decay the weights in a model using an L1 norm penalty. |
theanets.regularizers.WeightL2 ([pattern, weight]) |
Decay the weights in a model using an L2 norm penalty. |
theanets.trainer.DownhillTrainer (algo, network) |
Wrapper for using trainers from downhill . |
theanets.trainer.SampleTrainer (network) |
This trainer replaces network weights with samples from the input. |
theanets.trainer.SupervisedPretrainer (algo, ...) |
This trainer adapts parameters using a supervised pretraining approach. |
theanets.trainer.UnsupervisedPretrainer (...) |
Train a classification model using an unsupervised pre-training step. |