Markov chain Hebbian learning algorithm with ternary synaptic units

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, which is named as the Markov chain Hebbian learning algorithm. The algorithm pursues efficient memory use during training in that (i) the weight matrix has ternary elements (-1, 0, 1) and (ii) each update follows a Markov chain--the upcoming update does not need past weight memory. The algorithm was verified by two proof-of-concept tasks (handwritten digit recognition and multiplication table memorization) in which numbers were taken as symbols. 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 the arithmetic.

25 pages, 4 figures

References in corpus (4)

• Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Efficient supervised learning in networks with binary synapses
• Field-Programmable Crossbar Array (FPCA) for Reconfigurable Computing