Package pylearn

source code

Submodules

[hide private]

pylearn.algorithms
- pylearn.algorithms.aa
- pylearn.algorithms.cost: Cost functions.
- pylearn.algorithms.daa
- pylearn.algorithms.exponential_mean: Modules for maintaining statistics based on exponential decay
- pylearn.algorithms.kernel_regression: Implementation of kernel regression:
- pylearn.algorithms.layer: @todo: Make a layer class, with standardized names: input, cost, lr, and update (a Method called update, to be more precise, whose first argument is the input)
- pylearn.algorithms.linear_regression: Implementation of linear regression, with or without L2 regularization.
- pylearn.algorithms.logistic_regression
- pylearn.algorithms.minimizer: Define the interface and factory for gradient-based minimizers.
- pylearn.algorithms.rbm
- pylearn.algorithms.regressor
- pylearn.algorithms.rnn
- pylearn.algorithms.sandbox
  - pylearn.algorithms.sandbox.DAA_inputs_groups
  - pylearn.algorithms.sandbox._test_onehotop
  - pylearn.algorithms.sandbox.cost: Cost functions.
  - pylearn.algorithms.sandbox.kalman: Modules and misc.
  - pylearn.algorithms.sandbox.onehotop: One hot Op
  - pylearn.algorithms.sandbox.stat_ops
  - pylearn.algorithms.sandbox.test_cost
- pylearn.algorithms.sgd: A stochastic gradient descent minimizer.
- pylearn.algorithms.stacker
- pylearn.algorithms.stopper
- pylearn.algorithms.weights: Routine to initialize weights.
pylearn.dataset_ops
- pylearn.dataset_ops.MNIST: Regular MNIST using the dataset protocol
- pylearn.dataset_ops.cifar10: CIFAR-10 dataset of labeled small colour images.
- pylearn.dataset_ops.gldataset: Demonstrate a complicated dynamically-generated dataset.
- pylearn.dataset_ops.glviewer: This file provides a very crude image-viewing and movie-viewing mini-application.
- pylearn.dataset_ops.memo: Provide a decorator that caches expensive functions
- pylearn.dataset_ops.protocol: Convenience base classes to help with writing Dataset ops
- pylearn.dataset_ops.sandbox
  - pylearn.dataset_ops.sandbox.COIL100: http://www1.cs.columbia.edu/CAVE/software/softlib/coil-100.php
- pylearn.dataset_ops.shapeset1: A Theano Op to load/access Shapeset1
pylearn.datasets
- pylearn.datasets.MNIST: Various routines to load/access MNIST data.
- pylearn.datasets.cifar10: Various routines to load/access MNIST data.
- pylearn.datasets.config: Configuration options for datasets
- pylearn.datasets.dataset: The dataset-from-descriptor mechanism.
- pylearn.datasets.embeddings
  - pylearn.datasets.embeddings.convert: Convert stdin sentences to word embeddings, and output YAML.
  - pylearn.datasets.embeddings.parameters: Locations of the embedding data files.
  - pylearn.datasets.embeddings.percent
  - pylearn.datasets.embeddings.process: Read in the weights file
- pylearn.datasets.faces: Various routines to load/access faces datasets.
- pylearn.datasets.flickr: Routines to load variations on the Flickr image dataset.
- pylearn.datasets.image_patches: Routines to load/access Olshausen's image_patches
- pylearn.datasets.imagenet
- pylearn.datasets.make_test_datasets
- pylearn.datasets.miniblocks
- pylearn.datasets.nist_sd: Provides a Dataset to access the nist digits_reshuffled dataset.
- pylearn.datasets.norb_small
- pylearn.datasets.shapeset1: Routines to load/access Shapeset1
- pylearn.datasets.smallNorb
- pylearn.datasets.tagatune: Access the TagATune dataset from
- pylearn.datasets.testDataset: Various routines to load/access MNIST data.
- pylearn.datasets.test_tzanetakis
- pylearn.datasets.tzanetakis: Load Tzanetakis' genre-classification dataset.
pylearn.examples
- pylearn.examples.daa
- pylearn.examples.linear_classifier: T.
- pylearn.examples.theano_update
pylearn.exceptions: Common exceptions.
pylearn.external
- pylearn.external.wrap_libsvm
pylearn.io
- pylearn.io.amat: load PLearn AMat files
- pylearn.io.audio
- pylearn.io.filetensor: Read and write the matrix file format described at http://www.cs.nyu.edu/~ylclab/data/norb-v1.0/index.html
- pylearn.io.image_tiling: Illustrate filters (or data) in a grid of small image-shaped tiles.
- pylearn.io.pmat
- pylearn.io.seriestables
  - pylearn.io.seriestables.series
  - pylearn.io.seriestables.test_series
- pylearn.io.tests
  - pylearn.io.tests.test_filetensor
- pylearn.io.ubyte: Provides read_ubyte_matrix
- pylearn.io.wavread: WavRead Op
pylearn.lib
pylearn.sandbox
- pylearn.sandbox._test_random_transformation
- pylearn.sandbox.check_speed
- pylearn.sandbox.denoising_aa: A denoising auto-encoder
- pylearn.sandbox.gradient_learner
- pylearn.sandbox.image_tools
- pylearn.sandbox.nips09stopper: Early stopper
- pylearn.sandbox.random_transformation: New Ops that aren't in core theano
- pylearn.sandbox.rbm
  - pylearn.sandbox.rbm.main: Simple SGD RBM training.
  - pylearn.sandbox.rbm.model: The model for an autoassociator for sparse inputs, using Ronan Collobert + Jason Weston's sampling trick (2008).
  - pylearn.sandbox.rbm.parameters: Parameters (weights) used by the Model.
- pylearn.sandbox.scan_inputs_groups
- pylearn.sandbox.simple_autoassociator
  - pylearn.sandbox.simple_autoassociator.graph: Theano graph for a simple autoassociator.
  - pylearn.sandbox.simple_autoassociator.main: A simple autoassociator.
  - pylearn.sandbox.simple_autoassociator.model: The model for an autoassociator for sparse inputs, using Ronan Collobert + Jason Weston's sampling trick (2008).
  - pylearn.sandbox.simple_autoassociator.parameters: Parameters (weights) used by the Model.
- pylearn.sandbox.sparse_instance: Sparse instances.
- pylearn.sandbox.sparse_random_autoassociator
  - pylearn.sandbox.sparse_random_autoassociator.globals: Global variables.
  - pylearn.sandbox.sparse_random_autoassociator.graph: Theano graph for an autoassociator for sparse inputs, which will be trained using Ronan Collobert + Jason Weston's sampling trick (2008).
  - pylearn.sandbox.sparse_random_autoassociator.main: An autoassociator for sparse inputs, using Ronan Collobert + Jason Weston's sampling trick (2008).
  - pylearn.sandbox.sparse_random_autoassociator.model: The model for an autoassociator for sparse inputs, using Ronan Collobert + Jason Weston's sampling trick (2008).
  - pylearn.sandbox.sparse_random_autoassociator.parameters: Parameters (weights) used by the Model.
- pylearn.sandbox.statscollector
- pylearn.sandbox.test_scan_inputs_groups
pylearn.shared
- pylearn.shared.layers
  - pylearn.shared.layers.exponential_mean: Modules for maintaining statistics based on exponential decay
  - pylearn.shared.layers.kording2004
  - pylearn.shared.layers.kouh2008: Paper:
  - pylearn.shared.layers.lecun1998: Provide the convolution and pooling layers described in LeCun 98
  - pylearn.shared.layers.logreg: Provides LogisticRegression
  - pylearn.shared.layers.rust2005: Provides Rust2005 layer
  - pylearn.shared.layers.sandbox
    - pylearn.shared.layers.sandbox.adelsonbergen87: WRITEME
    - pylearn.shared.layers.sandbox.linsvm
  - pylearn.shared.layers.sgd: Provides StochasticGradientDescent, HalflifeStopper
  - pylearn.shared.layers.sigmoidal_layer: Provide the "normal" sigmoidal layers for making multi-layer perceptrons / neural nets
  - pylearn.shared.layers.squash: Provides a convenient lookup mechanism for squashing functions.
  - pylearn.shared.layers.util: A few little internal functions
pylearn.version

Functions

[hide private]

__src_version__()

source code

Imports: algorithms, dataset_ops, datasets, examples, exceptions, external, io, lib, sandbox, shared, version