Man pages for fdavidcl/ruta
Implementation of Unsupervised Neural Architectures
| add_weight_decay | Add weight decay to any autoencoder |
| apply_filter | Apply filters |
| as_loss | Coercion to ruta_loss |
| as_network | Coercion to ruta_network |
| autoencode | Automatically compute an encoding of a data matrix |
| autoencoder | Create an autoencoder learner |
| autoencoder_contractive | Create a contractive autoencoder |
| autoencoder_denoising | Create a denoising autoencoder |
| autoencoder_robust | Create a robust autoencoder |
| autoencoder_sparse | Sparse autoencoder |
| autoencoder_variational | Build a variational autoencoder |
| configure | Configure a learner object with the associated Keras objects |
| contraction | Contractive loss |
| conv | Create a convolutional layer |
| correntropy | Correntropy loss |
| decode | Retrieve decoding of encoded data |
| dense | Create a fully-connected neural layer |
| dropout | Dropout layer |
| encode | Retrieve encoding of data |
| encoding_index | Get the index of the encoding |
| evaluate | Evaluation metrics |
| evaluation_metric | Custom evaluation metrics |
| generate | Generate samples from a generative model |
| input | Create an input layer |
| is_contractive | Detect whether an autoencoder is contractive |
| is_denoising | Detect whether an autoencoder is denoising |
| is_robust | Detect whether an autoencoder is robust |
| is_sparse | Detect whether an autoencoder is sparse |
| is_trained | Detect trained models |
| is_variational | Detect whether an autoencoder is variational |
| join-networks | Add layers to a network/Join networks |
| layer_keras | Custom layer from Keras |
| loss_variational | Variational loss |
| make_contractive | Add contractive behavior to any autoencoder |
| make_denoising | Add denoising behavior to any autoencoder |
| make_robust | Add robust behavior to any autoencoder |
| make_sparse | Add sparsity regularization to an autoencoder |
| new_autoencoder | Create an autoencoder learner |
| new_layer | Layer wrapper constructor |
| new_network | Sequential network constructor |
| noise | Noise generator |
| noise_cauchy | Additive Cauchy noise |
| noise_gaussian | Additive Gaussian noise |
| noise_ones | Filter to add ones noise |
| noise_saltpepper | Filter to add salt-and-pepper noise |
| noise_zeros | Filter to add zero noise |
| output | Create an output layer |
| plot.ruta_network | Draw a neural network |
| print-methods | Inspect Ruta objects |
| reconstruct | Retrieve reconstructions for input data |
| save_as | Save and load Ruta models |
| sparsity | Sparsity regularization |
| sub-.ruta_network | Access subnetworks of a network |
| to_keras | Convert a Ruta object onto Keras objects and functions |
| to_keras.ruta_autoencoder | Extract Keras models from an autoencoder wrapper |
| to_keras.ruta_filter | Get a Keras generator from a data filter |
| to_keras.ruta_layer_input | Convert Ruta layers onto Keras layers |
| to_keras.ruta_layer_variational | Obtain a Keras block of layers for the variational... |
| to_keras.ruta_loss_named | Obtain a Keras loss |
| to_keras.ruta_network | Build a Keras network |
| to_keras.ruta_sparsity | Translate sparsity regularization to Keras regularizer |
| to_keras.ruta_weight_decay | Obtain a Keras weight decay |
| train.ruta_autoencoder | Train a learner object with data |
| variational_block | Create a variational block of layers |
| weight_decay | Weight decay |
