Analytical guarantees for reduced precision fixed-point margin hyperplane classifiers

Margin hyperplane classifiers such as support vector machines are strong predictive models having gained considerable success in various classification tasks. Their conceptual simplicity makes them suitable candidates for the design of embedded machine learning systems. Their accuracy and resource utilization can effectively be traded off each other through precision. We analytically capture this trade-off by means of bounds on the precision requirements of general margin hyperplane classifiers. In addition, we propose a principled precision reduction scheme based on the trade-off between input and weight precisions. Our analysis is supported by simulation results illustrating the gains of our approach in terms of reducing resource utilization. For instance, we show that a linear margin classifier with precision assignment dictated by our approach and applied to the `two vs. four' task of the MNIST dataset is ~2x more accurate than a standard 8 bit low-precision implementation in spite of using ~2x10^4 fewer 1 bit full adders and ~2x10^3 fewer bits for data and weight representation.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2018

Author dc:creator

• Sakr, Charbel

Contributors dc:contributor

• Shanbhag, Naresh R.

• Fixed-point machine learning

Statement dc:rights

• Copyright 2017 Charbel Sakr

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/99324

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/99324