Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity

Abstract

The liquid state machine (LSM) combines low training complexity and biological plausibility, which has made it an attractive machine learning framework for edge and neuromorphic computing paradigms. Originally proposed as a model of brain computation, the LSM tunes its internal weights without backpropagation of gradients, which results in lower performance compared to multi-layer neural networks. Recent findings in neuroscience suggest that astrocytes, a long-neglected non-neuronal brain cell, modulate synaptic plasticity and brain dynamics, tuning brain networks to the vicinity of the computationally optimal critical phase transition between order and chaos. Inspired by this disruptive understanding of how brain networks self-tune, we propose the neuron-astrocyte liquid state machine (NALSM) 1 that addresses under-performance through self-organized near-critical dynamics. Similar to its biological counterpart, the astrocyte model integrates neuronal activity and provides global feedback to spike-timing-dependent plasticity (STDP), which self-organizes NALSM dynamics around a critical branching factor that is associated with the edge-of-chaos. We demonstrate that NALSM achieves state-of-the-art accuracy versus comparable LSM methods, without the need for data-specific hand-tuning. With a top accuracy of 97.61% on MNIST, 97.51% on N-MNIST, and 85.84% on Fashion-MNIST, NALSM achieved comparable performance to current fully-connected multi-layer spiking neural networks trained via backpropagation. Our findings suggest that the further development of braininspired machine learning methods has the potential to reach the performance of deep learning, with the added benefits of supporting robust and energy-efficient neuromorphic computing on the edge.

Meta-SpikePropamine: learning to learn with synaptic plasticity in spiking neural networks

“…To realize the full potential of this framework, described here are several topics for future research, including: incorporating cell-type specific neuromodulatory signals (Liu et al, 2021) into the learning process; exploring the addition of glial cell dynamics (Gordleeva et al, 2021;Ivanov and Michmizos, 2021); providing deeper insight into the learning capabilities of different plasticity rules in the neuroscience literature, such as the widerange of existing voltage-dependent plasticity rules, rate-based plasticity rules, and spike-timing dependent plasticity rules; and exploring the use of this framework on robotic and reinforcement learning experiments. Another direction might explore learning the neural architecture in conjunction with the plasticity parameters, since architecture is known to play a significant role in the function of neural dynamics (Gaier and Ha, 2019).…”