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).
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2009
- Accession Number
- ADA529167
Entities
People
- Paul Hasler
Organizations
- Georgia Tech