Neuromorphic Overparameterisation and Few-Shot Learning in Multilayer Physical Neural Networks

Abstract

Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach's efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

References in corpus (16)

• Recent Advances in Physical Reservoir Computing: A Review
• Current-induced spin-orbit torques in ferromagnetic and antiferromagnetic systems
• Reconciling modern machine learning practice and the bias-variance trade-off
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Physical reservoir computing -- An introductory perspective
• Nanoscale neural network using non-linear spin-wave interference
• Reconfigurable Training and Reservoir Computing in an Artificial Spin-Vortex Ice via Spin-Wave Fingerprinting
• Dynamic response of an artificial square spin ice
• A perspective on physical reservoir computing with nanomagnetic devices
• Reconfigurable Reservoir Computing in a Magnetic Metamaterial
• Exploiting Multiple Timescales in Hierarchical Echo State Networks
• SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations
• Spectral-fingerprinting: Microstate readout via remanence ferromagnetic resonance in artificial spin systems
• Spatial Analysis of Physical Reservoir Computers
• Multilayer spintronic neural networks with radio-frequency connections
• Powering AI at the Edge: A Robust, Memristor-based Binarized Neural Network with Near-Memory Computing and Miniaturized Solar Cell

Cited by in corpus (7)

• Passive frustrated nanomagnet reservoir computing
• Artificial Spin Ice: A Tutorial on Design and Control of Geometry, Microstate, Magnon Dynamics & Neuromorphic Computing
• Snakes in the Plane: Controllable Gliders in a Nanomagnetic Metamaterial
• Predicting the future with magnons
• Magnetic texture control in ion-implanted metamaterials
• The dipolar Aleppo lattice: Ground state ordering and ergodic dynamics in the absence of vertex frustration
• Metrics for spin-based computing