CMOS-based Stochastically Spiking Neural Network for Optimization under Uncertainties

Abstract

We present CMOS-based 'stochastically spiking neural network' for optimization under uncertainties. We discuss a scenario generation circuit to non-parametrically estimate/emulate statistics of uncertain cost/constraints variables in an optimization problem. We also present a spiking neural network for linear/quadratic programming. Scenario generation block stochastically controls spiking neural network to extract optimal solution of an optimization problem minimizing its expected cost.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2017
Accession Number
AD1041633

Entities

People

  • Amit R. Trivedi
  • Saibal Mukhopadhyay

Organizations

  • University of Illinois at Chicago

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Amplifiers
  • Computations
  • Computer Programming
  • Computers
  • Demographic Cohorts
  • Engineering
  • Generators
  • Kernel Functions
  • Military Research
  • Neural Networks
  • Optimization
  • Quadratic Programming
  • Random Variables
  • Statistical Samples
  • Statistics
  • Uncertainty

Fields of Study

  • Computer science

Readers

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

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks