Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rodrigosetti/dbn-cuda
GPU accelerated Deep Belief Network
https://github.com/rodrigosetti/dbn-cuda
dbn dbn-cuda deep-belief-network deep-learning deep-neural-networks neural-networks
Last synced: 2 months ago
JSON representation
GPU accelerated Deep Belief Network
- Host: GitHub
- URL: https://github.com/rodrigosetti/dbn-cuda
- Owner: rodrigosetti
- Created: 2015-05-22T22:04:05.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2015-05-22T22:14:52.000Z (almost 10 years ago)
- Last Synced: 2024-07-30T18:02:10.327Z (7 months ago)
- Topics: dbn, dbn-cuda, deep-belief-network, deep-learning, deep-neural-networks, neural-networks
- Language: Python
- Size: 3.13 MB
- Stars: 47
- Watchers: 6
- Forks: 18
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
dbn-cuda
========GPU accelerated Deep Belief Network in Python
From [Wikipedia](http://en.wikipedia.org/wiki/Deep_belief_network):
> In machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a
> type of deep neural network, composed of multiple layers of latent variables ("hidden units"), with
> connections between the layers but not between units within each layer.> When trained on a set of examples in an unsupervised way, a DBN can
> learn to probabilistically reconstruct its inputs. The layers then act as feature detectors on inputs.
> After this learning step, a DBN can be further trained in a supervised way to perform classification.See the [example](example.ipynb).
Requirements
------------* [numpy](http://www.numpy.org)
* [cudamat](https://github.com/cudamat/cudamat)
* [PyPrind](https://pypi.python.org/pypi/PyPrind)