https://github.com/jfsantos/dbn.jl

A Deep Belief Network implementation in Julia
https://github.com/jfsantos/dbn.jl

Last synced: 11 days ago
JSON representation

A Deep Belief Network implementation in Julia

• Host: GitHub
• URL: https://github.com/jfsantos/dbn.jl
• Owner: jfsantos
• License: mit
• Created: 2014-11-26T14:23:25.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2014-12-12T05:06:03.000Z (about 10 years ago)
• Last Synced: 2024-12-10T15:05:13.094Z (17 days ago)
• Language: Julia
• Size: 215 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
**WARNING:** This is just a hack for now and completely untested. 

There is only support for a DBN where the first layer is a Gaussian-Bernoulli RBM and the subsequent layers are Bernoulli-Bernoulli RBMs. The goal is implement methods for training Deep Belief Networks in Julia. We are using the Restricted Boltzmann Machine implementation from [Boltzmann.jl](https://github.com/dfdx/Boltzmann.jl) and a HDF5 data source based on an implementation in [Mocha.jl](https://github.com/pluskid/Mocha.jl). We may either replace the latter with a simpler HDF5 source implementation or implement a training algorithm in a way that's more compatible with Mocha.