Classification Functions for Handwritten Digit Recognition

Tsutomu SASAO  Yuto HORIKAWA  Yukihiro IGUCHI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E104-D    No.8    pp.1076-1082
Publication Date: 2021/08/01
Publicized: 2021/04/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2020LOP0002
Type of Manuscript: Special Section PAPER (Special Section on Multiple-Valued Logic and VLSI Computing)
Category: Logic Design
Keyword: 
linear decomposition,  partially defined function,  support minimization,  classification,  digit recognition,  MNIST,  index generation function,  machine learning,  neural network,  ensemble method,  

Full Text: PDF(600.9KB)>>
Buy this Article



Summary: 
A classification function maps a set of vectors into several classes. A machine learning problem is treated as a design problem for partially defined classification functions. To realize classification functions for MNIST hand written digits, three different architectures are considered: Single-unit realization, 45-unit realization, and 45-unit ×r realization. The 45-unit realization consists of 45 ternary classifiers, 10 counters, and a max selector. Test accuracy of these architectures are compared using MNIST data set.


open access publishing via