Handwritten Digit Recognition Based on Classification Functions

Sasao, Tsutomu; Horikawa, Yuto; Iguchi, Yukihiro

doi:10.1109/ismvl49045.2020.00-18

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the performance is not critical, the max selector can be implemented by a sequential circuit. (16) inputs can be synthesized with two (four) 14-input LUTs, the network can be mapped into 227 × 2 = 454 BRAM18s. Note that each unit has two outputs.…”

Section: Max Selectormentioning

confidence: 99%

See 1 more Smart Citation

Classification Functions for Handwritten Digit Recognition

Sasao

Horikawa

Iguchi

2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Max Selectormentioning

confidence: 99%

“…A preliminary version of this paper was presented as [16]. In [16], threshold elements are used in the output parts, while in this paper, counters and max selectors are used. With this modification, the accuracy has been improved significantly.…”

Section: Introductionmentioning

confidence: 99%