Spoken digit classification using a spin-wave delay-line active-ring reservoir computing

2020/05/26 by Stuart Watt, Watt, Stuart, Mikhail Kostylev +1 · 1 citation
Computer Science · Engineering · #Neural Networks and Reservoir Computing #Optical Network Technologies #Photonic and Optical Devices

paper · pdf · doi:10.48550/arxiv.2005.12557

Abstract

As a test of general applicability, we use the recently proposed spin-wave delay line active-ring reservoir computer to perform the spoken digit recognition task. On this, classification accuracies of up to 93% are achieved. The tested device prototype employs improved spin wave transducers (antennas). Therefore, in addition, we also let the computer complete the short-term memory (STM) task and the parity check (PC) tasks, because the fading memory and nonlinearity are essential to reservoir computing performance. The resulting STM and PC capacities reach maximum values of 4.77 and 1.47 respectively.

Citations

• Recent advances in physical reservoir computing: A review

Cited by

• Technical Review of spin-based computing

Related

• Spoken Digit Classification by In-Materio Reservoir Computing with Neuromorphic Atomic Switch Networks
• Audio Classification with Skyrmion Reservoirs
• Digit classification using photonic reservoir computing based on a silicon microring resonator
• Hardware-Friendly Synaptic Orders and Timescales in Liquid State Machines for Speech Classification
• In-Materia Speech Recognition