Maximizing Computational Capability with Minimal Power

Abstract

Getting higher power efficiency: Neuromorphic Engineering -- 400MMAC/neuron at 20pW vs. digital and analog. Neuromorphic processing = event-based processing uses power only when useful signals are present ("always on" in sensors or further processing). Programmability and Configurability empowers neuromorphic design towards useful applications in a reasonable timeframe. - Address Event Representation ~ sizes of largest custom neuro ICs. Can model pryamidal cells in configurable fabric in ~1mm2 area with realistic channel, dendrite, and xynapse elements (power in nW level and decreasing).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2009
Accession Number
ADA529167

Entities

People

  • Paul Hasler

Organizations

  • Georgia Tech

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Adaptive Filters
  • Analog Signals
  • Computations
  • Computers
  • Digital Signal Processing
  • Education
  • Efficiency
  • Energy Efficiency
  • Engineering
  • Filters
  • Micro-Machines
  • Mobile Phones
  • Signal Processing
  • Software Prototyping
  • Transistors
  • Workshops

Readers

  • Integrated Circuit Design and Technology.
  • Systems Analysis and Design