First Advisor

Dan Hammerstrom

Date of Award

Winter 2020

Document Type

Thesis

Degree Name

Bachelor of Science (B.S.) in Computer Science and University Honors

Department

Computer Science

Language

English

Subjects

Natural computation, Neural networks (Computer science)

DOI

10.15760/honors.967

Abstract

We present research on an implementation of a biologically inspired Bayesian Confidence Propagation Neural Network (BCPNN). Based on previous work by Christopher Johansson and Anders Lansner, our implementation seeks to test and understand the various properties of this model. The floating-point implementation we built uses discrete time and bit-vectors as input/output. We found that the column based BCPNN model is able to memorize a decent number of input vectors and is able to restore noisy versions of these vectors with relatively high accuracy. We examine the model’s capacity, noise recovery ability and cross-column connection influence, among other attributes. The clearest trends that we found were in the capacity and noise recovery properties of the model, while the influence of cross-column connections was less clear. Further research and development of this model implementation is needed to increase speed, capacity and error correction capabilities.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

Persistent Identifier

https://archives.pdx.edu/ds/psu/34438

Download

Share

COinS