In-situ learning harnessing intrinsic resistive memory variability through Markov Chain Monte Carlo Sampling

TL;DR

This paper demonstrates in-situ Bayesian learning using resistive memory variability, turning a physical non-ideality into a computational advantage for edge AI applications.

Contribution

It introduces a novel in-memory learning approach that exploits resistive memory variability with MCMC sampling, enabling effective local learning at the edge.

Findings

Achieved 96.3% accuracy on supervised tasks

Outperformed software neural networks with same memory size

Validated approach on reinforcement learning with Cartpole

Abstract

Resistive memory technologies promise to be a key component in unlocking the next generation of intelligent in-memory computing systems that can act and learn locally at the edge. However, current approaches to in-memory machine learning focus often on the implementation of models and algorithms which cannot be reconciled with the true, physical properties of resistive memory. Consequently, these properties, in particular cycle-to-cycle conductance variability, are considered as non-idealities that require mitigation. Here by contrast, we embrace these properties by selecting a more appropriate machine learning model and algorithm. We implement a Markov Chain Monte Carlo sampling algorithm within a fabricated array of 16,384 devices, configured as a Bayesian machine learning model. The algorithm is realised in-situ, by exploiting the devices as random variables from the perspective of their cycle-to-cycle conductance variability. We train experimentally the memory array to perform an illustrative supervised learning task as well as a malignant breast tissue recognition task, achieving an accuracy of 96.3%. Then, using a behavioural model of resistive memory calibrated on array level measurements, we apply the same approach to the Cartpole reinforcement learning task. In all cases our proposed approach outperformed software-based neural network models realised using an equivalent number of memory elements. This result lays a foundation for a new path in-memory machine learning, compatible with the true properties of resistive memory technologies, that can bring localised learning capabilities to intelligent edge computing systems.