Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
This offers a potential sustainable alternative for power-hungry AI applications, though it appears incremental as it matches rather than surpasses existing performance.
The paper tackles the problem of power consumption in reservoir computing by introducing networks of differentiating neurons that only activate with input changes, achieving 90.65% accuracy on MNIST digit recognition comparable to existing approaches.
Reservoir Computing is a machine learning approach that uses the rich repertoire of complex system dynamics for function approximation. Current approaches to reservoir computing use a network of coupled integrating neurons that require a steady current to maintain activity. Here, we introduce a small world graph of differentiating neurons that are active only when there are changes in input as an alternative to integrating neurons as a reservoir computing substrate. We find the coupling strength and network topology that enable these small world networks to function as an effective reservoir. We demonstrate the efficacy of these networks in the MNIST digit recognition task, achieving comparable performance of 90.65% to existing reservoir computing approaches. The findings suggest that differentiating neurons can be a potential alternative to integrating neurons and can provide a sustainable future alternative for power-hungry AI applications.