Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units
- Markov Chain Hebbian Learning Algorithm With Ternary Synaptic Units
- 김인호; 김재욱; 블라디미르 코르니축; 김구현; DOHUN KIM; HYO CHEON WOO; JIHUN KIM; CHEOL SEONG HWANG; DOO SEOK JEONG
- Issue Date
- IEEE Access
- VOL 7-10223
- 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 efcient use in memory during training in that: 1) the weight matrix has ternary elements (􀀀 1, 0, 1) and 2) each update follows a Markov chainthe upcoming update does not need past weight values. The algorithm was veried 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.
- Appears in Collections:
- KIST Publication > Article
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.