/DeePy

A Python implementation of deep learning methodologies.

Primary LanguagePythonMIT LicenseMIT

Python Deep Learning Tools (DeePy)

An open-source Python implementation of popular tools and techniques in deep learning. The purpose of this repository is to provide high-quality deep learning and data analytics software.

Features

  • Vanilla neural network architectures
  • Neural networks supported by deep belief network (DBN) initialization
  • Stacked autoencoders
If you like project and want to cite this toolbox, please use the following citation:

Brofos, James A., and Ajay Kannan. Python Python Deep Learning Tools (DeePy). Computer software. 
Vers. 0.1. GitHub, Inc., 08 Feb. 2014. Web. [DD] [MM]. [YYYY].

Demo

Dependencies

Python Financial Tools relies on the libraries listed below:

  • Numpy Standard numerical computations with vectors
  • Scipy Used for calculations involving statistical distributions

Citation

We were inspired to create this toolbox by the excellent work of Rasmus Berg Palm. Please see his MATLAB toolbox for deep learning.

R. B. Palm. "Prediction as a candidate for learning deep hierarchical models of data". 
Masters thesis. 2012. 08 Mar. 2014.