EnergyBasedModels-pytorch

Energy-based models in Pytorch

Author: Alejandro Pozas Kerstjens

Implementation of different generative models based on energy-based learning. Examples are provided with the MNIST dataset.

Libraries required:

• pytorch >= 0.4.0 as ML framework
• numpy for math operations
• matplotlib for image visualization
• tqdm for custom progress bar
• imageio for exporting outputs to .gif format

1. RBM

Restricted Boltzmann Machine with binary visible and hidden units. Although in this example it is used as a generative model, RBMs can also perform supervised tasks.

Example

2. Continuous RBM

Restricted Boltzmann Machine with binary hidden but continuous visible units.

Example

3. Deep Belief Network

Deep belief network with greedy pre-training plus global finetuning. A parameter of the model can do the visible layer to contain binary or continuous units.

Example

4. To-Do list

• Implement Persistent Contrastive Divergence for training
• Deep Belief Network with binary visible units
• Deep Belief Network with continuous visible units