Accession Number:

AD1046462

Title:

VINE: A Variational Inference -Based Bayesian Neural Network Engine

Descriptive Note:

Technical Report,01 Oct 2016,01 Aug 2017

Corporate Author:

University of Southern California Los Angeles United States

Personal Author(s):

• Pedram,Massoud
• Wang,Yanzhi

Report Date:

2018-01-01

Pagination or Media Count:

26.0

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.

Descriptors:

• learning machines
• ARTIFICIAL NEURAL NETWORKS
• inference engines
• RANDOM NUMBER GENERATORS

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE