BCAP: An Artificial Neural Network Pruning Technique to Reduce Overfitting

Thumbnail Image

Files

Brantley_umbc_0434M_11466.pdf (873.12 KB)
BrantleySupplementSlides.pdf (4.75 MB)

Links to Files

Permanent Link

http://hdl.handle.net/11603/15471

Collections

UMBC Theses and Dissertations

Author/Creator

Author/Creator ORCID

Date

2016-01-01

Type of Work

theses
Text

Department

Computer Science and Electrical Engineering

Program

Computer Science

Citation of Original Publication

Rights

This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Distribution Rights granted to UMBC by the author.

Subjects

Deep Learning
Neural Network Optimization
Neural Networks
Pruning Neural Networks

Abstract

Determining the optimal size of a neural network is complicated. Neural networks, with many free parameters, can be used to solve very complex problems. However, these neural networks are susceptible to overfitting. BCAP (Brantley-Clark Artificial Neural Network Pruning Technique) addresses overfitting by combining duplicate neurons in a neural network hidden layer, thereby forcing the network to learn more distinct features. We compare hidden units using the cosine similarity, and combine those that are similar with each other within a threshold. By doing so the co-adaption of the neurons in the network is reduced because hidden units that are highly correlated (i.e. similar) are combined. In this paper we show evidence that BCAP is successful in reducing network size while maintaining accuracy, or improving accuracy of neural networks during and after training.