SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations

Abstract

"Sparse" neural networks, in which relatively few neurons or connections are active, are common in both machine learning and neuroscience. Whereas in machine learning, "sparsity" is related to a penalty term that leads to some connecting weights becoming small or zero, in biological brains, sparsity is often created when high spiking thresholds prevent neuronal activity. Here we introduce sparsity into a reservoir computing network via neuron-specific learnable thresholds of activity, allowing neurons with low thresholds to contribute to decision-making but suppressing information from neurons with high thresholds. This approach, which we term "SpaRCe", optimises the sparsity level of the reservoir without affecting the reservoir dynamics. The read-out weights and the thresholds are learned by an on-line gradient rule that minimises an error function on the outputs of the network. Threshold learning occurs by the balance of two opposing forces: reducing inter-neuronal correlations in the reservoir by deactivating redundant neurons, while increasing the activity of neurons participating in correct decisions. We test SpaRCe on classification problems and find that threshold learning improves performance compared to standard reservoir computing. SpaRCe alleviates the problem of catastrophic forgetting, a problem most evident in standard echo state networks and recurrent neural networks in general, due to increasing the number of task-specialised neurons that are included in the network decisions.

References in corpus (9)

• Recent Advances in Physical Reservoir Computing: A Review
• Vowel recognition with four coupled spin-torque nano-oscillators
• Physical reservoir computing -- An introductory perspective
• Learning with Structured Sparsity
• Overcoming catastrophic forgetting with hard attention to the task
• Measuring Catastrophic Forgetting in Neural Networks
• Reservoir computing with the frequency, phase and amplitude of spin-torque nano-oscillators
• Exploiting Multiple Timescales in Hierarchical Echo State Networks
• Reservoir Computing meets Recurrent Kernels and Structured Transforms

Cited by in corpus (10)

• A perspective on physical reservoir computing with nanomagnetic devices
• Reconfigurable Reservoir Computing in a Magnetic Metamaterial
• Exploiting Multiple Timescales in Hierarchical Echo State Networks
• Neuromorphic Overparameterisation and Few-Shot Learning in Multilayer Physical Neural Networks
• Reservoir Computing Benchmarks: a tutorial review and critique
• EchoVPR: Echo State Networks for Visual Place Recognition
• Artificial Spin Ice: A Tutorial on Design and Control of Geometry, Microstate, Magnon Dynamics & Neuromorphic Computing
• Metrics for spin-based computing
• Quantifying the Computational Capability of a Nanomagnetic Reservoir Computing Platform with Emergent Magnetization Dynamics
• Dynamic Reservoir Computing with Physical Neuromorphic Networks