Ant Colony Optimization Applied to the Training of a High Order Neural Networks with Adaptable Exponential Weights

Abstract

High order neural networks (HONN) are neural networks which employ neurons that combine their inputs non-linearly. The HONEST (High Order Network with Exponential SynapTic links) network is a HONN that uses neurons with product units and adaptable exponents. The output of a trained HONEST network can be expressed in terms of the network inputs by a polynomial-like equation. This makes the structure of the network more transparent and easier to interpret. This study adapts ACOR, an Ant Colony Optimization algorithm, to the training of an HONEST network. Using a collection of 10 widely-used benchmark datasets, we compare ACOR to the well-known gradient-based Resilient Propagation (R-Prop) algorithm, in the training of HONEST networks. We find that our adaptation of ACOR has better test set generalization than R-Prop, though not to a statistically significant extent.

Department(s)

Electrical and Computer Engineering

Research Center/Lab(s)

Center for High Performance Computing Research

Second Research Center/Lab

Intelligent Systems Center

Comments

Chapter 14

International Standard Book Number (ISBN)

978-1522500636

Document Type

Book - Chapter

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2016 IGI Global, All rights reserved.

Publication Date

01 May 2016

Link to Full Text

Share

 
COinS