Classification Functions for Handwritten Digit Recognition

Tsutomu SASAO; Yuto HORIKAWA; Yukihiro IGUCHI

doi:10.1587/transinf.2020LOP0002

Special Section on Multiple-Valued Logic and VLSI Computing

Classification Functions for Handwritten Digit Recognition

Tsutomu SASAO, Yuto HORIKAWA, Yukihiro IGUCHI

著者情報

キーワード: linear decomposition, partially defined function, support minimization, classification, digit recognition, MNIST, index generation function, machine learning, neural network, ensemble method

ジャーナルフリー

2021 年 E104.D 巻 8 号 p. 1076-1082

DOI https://doi.org/10.1587/transinf.2020LOP0002

詳細

抄録

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.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）