Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units
- Title
- Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units
- Author
- 정두석
- Keywords
- Greedy edge-wise training; Hebbian learning; Markov chain; mental arithmetic; prime factorization; ternary unit
- Issue Date
- 2019-01
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Citation
- IEEE ACCESS, v. 7, Page. 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.
- URI
- https://ieeexplore.ieee.org/document/8607972https://repository.hanyang.ac.kr/handle/20.500.11754/102951
- ISSN
- 2169-3536
- DOI
- 10.1109/ACCESS.2018.2890543
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > MATERIALS SCIENCE AND ENGINEERING(신소재공학부) > Articles
- Files in This Item:
- Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units.pdfDownload
- Export
- RIS (EndNote)
- XLS (Excel)
- XML