Assembly output codes for learning neural networks

Neural network-based classifiers usually encode the class labels of input data via a completely disjoint code, i.e. a binary vector with only one bit associated with each category. We use coding theory to propose assembly codes where each element is associated with several classes, making for better...

Full description

Saved in:
Bibliographic Details
Published in2016 9th International Symposium on Turbo Codes and Iterative Information Processing (ISTC) pp. 285 - 289
Main Authors Tigreat, Philippe, Lassance, Carlos Rosar Kos, Xiaoran Jiang, Gripon, Vincent, Berrou, Claude
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2016
Subjects
Assembly coding
Classification
Clustered Clique Networks
Coding theory
Deep Learning
ECOC
Online AccessGet full text

Cover

More Information
Summary:Neural network-based classifiers usually encode the class labels of input data via a completely disjoint code, i.e. a binary vector with only one bit associated with each category. We use coding theory to propose assembly codes where each element is associated with several classes, making for better target vectors. These codes emulate the combination of several classifiers, which is a well-known method to improve decision accuracy. Our experiments on data-sets such as MNIST with a multi-layer neural network show that assembly output codes, which are characterized by a higher minimum Hamming distance, result in better classification performance. These codes are also well suited to the use of clustered clique-based networks in category representation.
ISSN:2165-4719
DOI:10.1109/ISTC.2016.7593122