VINE: A Variational Inference -Based Bayesian Neural Network Engine

Abstract

This report describes our findings and results for the DARPA MTO seedling project titled SpiNN-SC: Stochastic Computing-Based Realization of Spiking Neural Networks also known as VINE: A Variational Inference-Based Bayesian Neural Network Engine. The primary goal was to develop a Bayesian Neural Network (BNN) with an integrated Variational Inference (VI) engine to perform inference and learning (statically and on-the-fly) under uncertain or incomplete input and output features. A secondary goal is to enable robust decision making under noise and variability in the observed data and without reference to a ground truth. The key expected impact is to enable a new generation of BNNs that can operate on input and output features specified as random variables, that admit efficient hardware realization, and that can not only do inference but also can be retrained on-the-fly based on incoming data.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2018
Accession Number
AD1046462

Entities

People

  • Massoud Pedram
  • Yanzhi Wang

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence Software
  • Computer Programming
  • Computer Programs
  • Computers
  • Data Science
  • Dimensionality Reduction
  • Fungi
  • Information Science
  • Machine Learning
  • Monte Carlo Method
  • Neural Networks
  • Probability
  • Random Number Generators
  • Random Variables

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks