MURI17: Cross-disciplinary Electronic-ionic Research Enabling Biologically Realistic Autonomous Learning (CEREBRAL)
Abstract
We propose to implement a biomimetic, non-silicon, low power multi-layer 3D, adaptiveneuristor with thermally engineered broadened timing windows useful for stochastic learningenhancements that combines Neuromorphic and Boolean computation for vision analysis. Todo this, significant advancement in materials discovery relating to stoichiometry, correlationand disorder effects are proposed using state of the art toolsets providing discernment into thehidden quantum state density and charge occupancy internal state variables of adaptiveoxides. This fundamental materials research will enable key device innovations including twonever realized devices, and a new “Adaptive” building block akin to a biological neuron/axon.Using the novel quantum properties of these adaptive oxide materials, an adaptive timewindow for Spike Timing Dependent Plasticity (STDP), and new approaches to stochasticcircuitry, a 3D scalable, ultra-low voltage (mV range) artificial retina will be demonstratedthat can finally deliver the low power operation promised by Neuromorphic circuits. Theseinnovations will leverage the adaptive oxide materials quantum properties into new devicesand circuits to (1) exploit device noise to provide stochasticity and (2) control theprogrammable spike time window facilitating on-line, unsupervised learning.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Apr 09, 2018
- Source ID
- FA95501810024
Entities
People
- W. Alan Doolittle
Organizations
- Air Force Office of Scientific Research
- Georgia Tech Research Corporation
- United States Air Force