Enabling Brain-Inspired Processors through Energy-Efficient Delayed Feedback Reservoir Computing Integrated Circuits
Technical Report,01 Jun 2018,31 Dec 2019
Virginia Polytechnic Institute and State University Blacksburg United States
Pagination or Media Count:
Reservoir computing RC, an emerging machine learning paradigm, is considered a simplification of a conventional recurrent neural network. RC offers a unique learning mechanism at the readout stage that accelerates learning and computing operations. The objective of this project was to build a new class of computationally-efficient delayed feedback reservoir systems. The final outcome of this project was a Delayed Feedback Reservoir processor designed to exploit recent advancements in machine learning, integrated circuits, and nanotechnology.