Huffman Coding for Storing Non-uniformly Distributed Messages in Networks of Neural Cliques
A new family of sparse neural networks achieving nearly optimal performance has been recently introduced. In these networks, messages are stored as cliques in clustered graphs. In this paper, we interpret these networks using the formalism of error correcting codes. To achieve this, we introduce two original codes, the thrifty code and the clique code, that are both sub-families of binary constant weight codes. We also provide the networks with an enhanced retrieving rule that enables a property of answer correctness and that improves performance.
Download manuscript.
Bibtex@inproceedings{BogGriSegHei20147,
author = {Bartosz Boguslawski and Vincent Gripon and
Fabrice Seguin and Frédéric Heitzmann},
title = {Huffman Coding for Storing Non-uniformly
Distributed Messages in Networks of Neural Cliques},
booktitle = {proceedings of the Twenty-Eighth AAAI
Conference on Artificial Intelligence, volume 1},
year = {2014},
pages = {262--268},
month = {July},
}
|
|
You are the 2092787th visitor
|