Markov chain Hebbian learning algorithm with ternary synaptic units
This work addresses the need for efficient, real-time learning algorithms in machine learning, though it appears incremental as it builds on Hebbian learning with ternary weights and Markov chains.
The authors tackled the problem of real-time online learning by proposing a Markov chain Hebbian learning algorithm with ternary synaptic units, which achieved proof-of-concept verification on tasks like handwritten digit recognition and multiplication table memorization, demonstrating feasibility without providing concrete performance numbers.
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.