Neural Networks¶
nn
is an experimental module to train Neural Networks in PyTorch
that find the sparsest solution of \(P_0^\epsilon\) problem.
PyTorch implementation of AutoEncoders that form sparse representations.
|
Basis Matching Pursuit (ADMM) AutoEncoder neural network for sparse coding. |
|
Learned Iterative Shrinkage-Thresholding Algorithm [Rf8e51fb15445-1] AutoEncoder neural network for sparse coding. |
Basis Pursuit (BP) solvers (refer to Relaxation algorithms) PyTorch API.
|
Basis Pursuit solver for the \(Q_1^\epsilon\) problem |
Matching Pursuit Trainers.
|
Train |
|
Train LISTA with the original loss, defined in the paper as MSE between the latent vector Z (forward pass of LISTA NN) and the best possible latent vector Z*, obtained by running Basis Pursuit ADMM (shows better results that using original ISTA as the ground truth) on input X. |
|
Test Matching Pursuit with the fixed Softshrink threshold (embedded in a model) and trained weights. |
|
Swipe through a range of Softshrink threshold parameters |