Markov chain Hebbian learning algorithm with ternary synaptic units

TL;DR

This paper introduces a real-time, memory-efficient learning algorithm called Markov chain Hebbian learning with ternary synaptic units, suitable for online learning and capable of performing tasks like digit recognition and arithmetic memorization.

Contribution

The paper proposes a novel Markov chain Hebbian learning algorithm with ternary weights that enables efficient online learning without needing past weight memory.

Findings

Successfully applied to handwritten digit recognition.

Effective in memorizing multiplication tables.

Provides insights into memory-based arithmetic and factorization.

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.