Temporal credit assignment for one-shot learning utilizing a phase transition material

TL;DR

This paper demonstrates how VO2 phase transition materials can emulate various neuronal timescales and facilitate one-shot learning, leading to more efficient neural network training with fewer trials.

Contribution

It introduces a novel use of VO2 devices to mimic neuronal dynamics and temporal credit assignment, advancing hardware-based biologically inspired learning mechanisms.

Findings

VO2 devices can access a continuum of resistance states.

Device relaxation times can be tuned from milliseconds to seconds.

Neural network simulations show up to 4x fewer trials for learning.

Abstract

Design of hardware based on biological principles of neuronal computation and plasticity in the brain is a leading approach to realizing energy- and sample-efficient artificial intelligence and learning machines. An important factor in selection of the hardware building blocks is the identification of candidate materials with physical properties suitable to emulate the large dynamic ranges and varied timescales of neuronal signaling. Previous work has shown that the all-or-none spiking behavior of neurons can be mimicked by threshold switches utilizing phase transitions. Here we demonstrate that devices based on a prototypical metal-insulator-transition material, vanadium dioxide (VO2), can be dynamically controlled to access a continuum of intermediate resistance states. Furthermore, the timescale of their intrinsic relaxation can be configured to match a range of biologically-relevant timescales from milliseconds to seconds. We exploit these device properties to emulate three aspects of neuronal analog computation: fast (~1 ms) spiking in a neuronal soma compartment, slow (~100 ms) spiking in a dendritic compartment, and ultraslow (~1 s) biochemical signaling involved in temporal credit assignment for a recently discovered biological mechanism of one-shot learning. Simulations show that an artificial neural network using properties of VO2 devices to control an agent navigating a spatial environment can learn an efficient path to a reward in up to 4 fold fewer trials than standard methods. The phase relaxations described in our study may be engineered in a variety of materials, and can be controlled by thermal, electrical, or optical stimuli, suggesting further opportunities to emulate biological learning.