Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units

Authors
Kim, GuhyunKornijcuk, VladimirKim, DohunKim, InhoKim, JaewookWoo, Hyo CheonKim, JihunHwang, Cheol SeongJeong, Doo Seok
Issue Date
2019-01
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation
IEEE ACCESS, v.7, pp.10208 - 10223
Abstract
In spite of remarkable progress in machine learning techniques, the state-of-the-art machine learning algorithms often keep machines from real-time learning (online learning) due, in part, to computational complexity in parameter optimization. As an alternative, a learning algorithm to train a memory in real time is proposed, named the Markov chain Hebbian learning algorithm. The algorithm pursues efficient use in memory during training in that: 1) the weight matrix has ternary elements (-1, 0, 1) and 2) each update follows a Markov chain-the upcoming update does not need past weight values. The algorithm was verified by two proof-of-concept tasks: image (MNIST and CIFAR-10 datasets) recognition and multiplication table memorization. Particularly, the latter bases multiplication arithmetic on memory, which may be analogous to humans' mental arithmetic. The memory-based multiplication arithmetic feasibly offers the basis of factorization, supporting novel insight into memory-based arithmetic.
Keywords
SINGLE NEURONS; DEEP; MEMORY; NETWORKS; SINGLE NEURONS; DEEP; MEMORY; NETWORKS; Greedy edge-wise training; Hebbian learning; Markov chain; mental arithmetic; prime factorization; supervised learning; ternary unit
ISSN
2169-3536
URI
https://pubs.kist.re.kr/handle/201004/120512
DOI
10.1109/ACCESS.2018.2890543
Appears in Collections:
KIST Article > 2019
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE