GeneSys: enabling continuous learning through neural network evolution in hardware

Modern deep learning systems rely on (a) a hand-tuned neural network topology, (b) massive amounts of labelled training data, and (c) extensive training over large-scale compute resources to build a system that can perform efficient image classification or speech recognition. Unfortunately, we are s...

Full description

Saved in:

Bibliographic Details
Main Authors:	Samajdar, Ananda, Mannan, Parth, Garg, Kartikay, Krishna, Tushar
Format:	Conference Proceeding
Language:	English
Subjects:	accelerator adam artificial intelligence Artificial neural networks Bioinformatics Computing methodologies Computing methodologies > Machine learning Computing methodologies > Machine learning > Machine learning approaches Computing methodologies > Machine learning > Machine learning approaches > Neural networks continuous learning Engines eve general purpose Genomics hardware hardware software codesign microarchitecture SoC Sociology Statistics Topology
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!