Stochastic Computation

Author: Cortese, John Anthony

Year: 1995

Degree: Dissertation (Ph.D.)

Advisor: Goodman, Rodney M.

Committee Members: Franklin, Joel N.; Simon, Marvin K.; Goodman, Rodney M.; Abu-Mostafa, Yaser S.; Psaltis, Demetri

Option: Electrical Engineering

DOI: 10.7907/W627-YA05

Abstract

This thesis approaches computation from a communication theory perspective. Data is given to a computer, which is asked to arrive at a binary hypothesis decision. The computation task is viewed as a signal drawn from an ensemble, corrupted by noise, and passed to a receiver which is asked to make a binary signal detection decision.

To illustrate the approach, learning in a neural network is studied. An algorithm based on statistical communication techniques is developed which allows the determination of the neural network size, architecture, and system parameters. The computation, as interpreted in the communication framework, is assigned an equivalent channel capacity which measures the effectiveness with which the computing system extracts information in the Shannon sense from the input data. Numerical simulations of a neural network recognizing handwritten digits are used to illustrate key points.

Files