Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 정두석 | - |
dc.date.accessioned | 2019-04-29T08:05:26Z | - |
dc.date.available | 2019-04-29T08:05:26Z | - |
dc.date.issued | 2019-01 | - |
dc.identifier.citation | IEEE ACCESS, v. 7, Page. 10208-10223 | en_US |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/8607972 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/102951 | - |
dc.description.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. | en_US |
dc.description.sponsorship | This work was supported by the Brain Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT under Grant 2018M3C7A1056512. The work of C.S. Hwang and D.S. Jeong was supported by the Korea Institute of Science and Technology Open Research Program under Grant 2E27331. | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | en_US |
dc.subject | Greedy edge-wise training | en_US |
dc.subject | Hebbian learning | en_US |
dc.subject | Markov chain | en_US |
dc.subject | mental arithmetic | en_US |
dc.subject | prime factorization | en_US |
dc.subject | ternary unit | en_US |
dc.title | Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units | en_US |
dc.type | Article | en_US |
dc.relation.volume | 7 | - |
dc.identifier.doi | 10.1109/ACCESS.2018.2890543 | - |
dc.relation.page | 10208-10223 | - |
dc.relation.journal | IEEE ACCESS | - |
dc.contributor.googleauthor | Kim, Guhyun | - |
dc.contributor.googleauthor | Kornijcuk, Vladimir | - |
dc.contributor.googleauthor | Kim, Dohun | - |
dc.contributor.googleauthor | Kim, Inho | - |
dc.contributor.googleauthor | Kim, Jaewook | - |
dc.contributor.googleauthor | Woo, Hyo Cheon | - |
dc.contributor.googleauthor | Kim, Jihun | - |
dc.contributor.googleauthor | Hwang, Cheol Seong | - |
dc.contributor.googleauthor | Jeong, Doo Seok | - |
dc.relation.code | 2019036307 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DIVISION OF MATERIALS SCIENCE AND ENGINEERING | - |
dc.identifier.pid | dooseokj | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.