Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing

TL;DR

This paper presents a novel approach combining learning-to-learn with phase-change memory-based in-memory computing hardware to enable rapid, low-power adaptation of AI models for tasks like image classification and robotic control.

Contribution

It introduces a hardware-software co-design that leverages phase-change memory neuromorphic hardware for efficient meta-learning, demonstrating rapid adaptation with minimal updates.

Findings

Models perform on par with software counterparts.

Rapid learning with few parameter updates.

Meta-training can be done in software with high precision.

Abstract

There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain's operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates. Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models.