Date of Graduation

12-2015

Document Type

Thesis

Degree Name

Master of Science in Computer Science (MS)

Degree Level

Graduate

Department

Computer Science & Computer Engineering

Advisor

Michael Gashler

Committee Member

John Gauch

Second Committee Member

Wing Ning Li

Keywords

Applied sciences, Forward bipartite alignment, Machine learning, Neutral network

Abstract

We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still generalize differently. FBA enables a diversity of applications, including visualization and canonicalization of neural networks, ensembles, and cross-over between unrelated neural networks in evolutionary optimization. We describe the FBA algorithm, and describe implementations for three applications: genetic algorithms, visualization, and ensembles. We demonstrate FBA's usefulness by comparing a bag of neural networks to a bag of FBA-aligned neural networks. We also show that aligning, and then combining two neural networks has no appreciable loss in accuracy which means that Forward Bipartite Alignment aligns neural networks in a meaningful way.

Share

COinS