https://github.com/cossio/standardizedrestrictedboltzmannmachines.jl

https://github.com/cossio/standardizedrestrictedboltzmannmachines.jl

Last synced: 10 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/cossio/standardizedrestrictedboltzmannmachines.jl
• Owner: cossio
• License: mit
• Created: 2023-04-20T20:55:33.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2024-07-08T19:36:28.000Z (4 months ago)
• Last Synced: 2024-07-10T02:29:18.993Z (4 months ago)
• Language: Jupyter Notebook
• Size: 347 KB
• Stars: 0
• Watchers: 2
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# StandardizedRestrictedBoltzmannMachines Julia package

Train and sample a *standardized* Restricted Boltzmann machine in Julia. The energy is given by:

$$E(\mathbf{v},\mathbf{h}) = - \sum_{i}\theta_{i}v_{i} - \sum_{\mu}\theta_{\mu}h_{\mu} - \sum_{i\mu}w_{i\mu} \frac{v_{i} - \lambda_{i}}{\sigma_{i}}\frac{h_{\mu} - \lambda_{\mu}}{\sigma_{\mu}}$$

with some offset parameters $\lambda_i,\lambda_\mu$ and scaling parameters $\sigma_i,\sigma_\mu$. Usually $\lambda_i,\lambda_\mu$ track the mean activities of visible and hidden units, while $\sigma_i,\sigma_\mu$ track their standard deviations.

## Installation

This package is registered. Install with:

```julia

using Pkg

Pkg.add("StandardizedRestrictedBoltzmannMachines")

```

This package does not export any symbols.

## Related

* https://github.com/cossio/RestrictedBoltzmannMachines.jl.