Reservoir Computing with VCO-Based Spiking Neurons for Regression and Classification
Reservoir computing (RC) significantly reduces the requirement on hardware and training resources, making it suitable for edge-computing applications. This work proposes using voltage-controlled oscillator (VCO)-based spiking neurons for RC to leverage the intrinsic randomness and variability of the neuron circuit for low-power operations. We describe the underlying circuit design and propose a network architecture based on the spiking neuron for RC. We demonstrate the effectiveness of the proposed RC network using VCO-based spiking neurons through benchmark tasks and electrocardiogram (ECG) classification.
Authors
- Parker Allred (ORCID: https://orcid.org/0000-0003-1720-3368)
- Yen‐Cheng Kuan (ORCID: https://orcid.org/0000-0001-7026-4595)
- Taylor Barton (ORCID: https://orcid.org/0009-0002-9405-5303)
- Shiuh-Hua Wood Chiang (ORCID: https://orcid.org/0000-0001-8091-6569)
- Hakaru Tamukoh (ORCID: https://orcid.org/0000-0002-3669-1371)
- Kanta Yoshioka
- Bibhu Datta Sahoo (ORCID: https://orcid.org/0000-0002-3563-9096)
Institutions
- Brigham Young University (US)
- National Yang Ming Chiao Tung University (TW)
- Kyushu Institute of Technology (JP)
- University at Buffalo, State University of New York (US)
Publication Details
- Published
- 2025-05-25
- DOI
- https://doi.org/10.1109/iscas56072.2025.11043229
- Citations
- 1
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Ministry of Education
- Technology Development