DOE CODE   /    Search Results   /    Cortexsys v. 3.0

Cortexsys v. 3.0

RESOURCE

Publicly Accessible Repository
https://github.com/sandialabs/Cortexsys
https://doi.org/10.11578/dc.20171025.1745

SAVE / SHARE



SNL Badge

Abstract

This code implements a variety of "deep learning" algorithms from openly published academic journals. These deep learning algorithms allow the user to train neural networks to do various tasks. Such tasks include predicting future values in a time sequence, categorizing images or compressing information. The code is mostly written in the easy to understand Matlab / GNU Octave language, which enables rapid prototyping and understanding for research and educational purposes.
Developers:
Cox, Jonathan [1]
  1. Sandia National Laboratories
Release Date:
2016-03-07
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
C++
C
MATLAB
M
Cuda
Version:
3.0
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
4127
Site Accession Number:
SCR# 2090.0
Research Org.:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Country of Origin:
United States

RESOURCE

Publicly Accessible Repository
https://github.com/sandialabs/Cortexsys
https://doi.org/10.11578/dc.20171025.1745

SAVE / SHARE



SNL Badge

Citation Formats

Cox, Jonathan A. Cortexsys v. 3.0. Computer Software. https://github.com/sandialabs/Cortexsys. USDOE. 07 Mar. 2016. Web. doi:10.11578/dc.20171025.1745.
Cox, Jonathan A. (2016, March 07). Cortexsys v. 3.0. [Computer software]. https://github.com/sandialabs/Cortexsys. https://doi.org/10.11578/dc.20171025.1745.
Cox, Jonathan A. "Cortexsys v. 3.0." Computer software. March 07, 2016. https://github.com/sandialabs/Cortexsys. https://doi.org/10.11578/dc.20171025.1745.
@misc{ doecode_4127,
title = {Cortexsys v. 3.0},
author = {Cox, Jonathan A.},
abstractNote = {This code implements a variety of "deep learning" algorithms from openly published academic journals. These deep learning algorithms allow the user to train neural networks to do various tasks. Such tasks include predicting future values in a time sequence, categorizing images or compressing information. The code is mostly written in the easy to understand Matlab / GNU Octave language, which enables rapid prototyping and understanding for research and educational purposes.},
doi = {10.11578/dc.20171025.1745},
url = {https://doi.org/10.11578/dc.20171025.1745},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20171025.1745}},
year = {2016},
month = {mar}
}