Enabling Brain-Inspired Processors through Energy-Efficient Delayed Feedback Reservoir Computing Integrated Circuits

Abstract

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 19, 2020
Accession Number
AD1101848

Entities

People

  • Yi Yang

Organizations

  • Virginia Tech

Tags

Communities of Interest

  • Advanced Electronics
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Application-Specific Integrated Circuits
  • Artificial Intelligence Software
  • Complementary Metal-Oxide Semiconductors
  • Computational Science
  • Electronic Circuits
  • Energy Consumption
  • Information Processing
  • Information Science
  • Information Systems
  • Integrated Circuits
  • Machine Learning
  • Metal Oxide Semiconductors
  • Neural Networks
  • Recurrent Neural Networks
  • Reservoir Computing
  • Semiconductors

Fields of Study

  • Computer science

Readers

  • Integrated Circuit Design and Technology.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Biotechnology