Files in this item



application/pdfSAKR-THESIS-2017.pdf (4MB)
(no description provided)PDF


Title:Analytical guarantees for reduced precision fixed-point margin hyperplane classifiers
Author(s):Sakr, Charbel
Advisor(s):Shanbhag, Naresh R.
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Fixed-point machine learning
Abstract: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.
Issue Date:2017-11-10
Rights Information:Copyright 2017 Charbel Sakr
Date Available in IDEALS:2018-03-13
Date Deposited:2017-12

This item appears in the following Collection(s)

Item Statistics