SYSTEM AND METHOD FOR MODEL COMPRESSION OF NEURAL NETWORKS FOR USE IN EMBEDDED PLATFORMS

Embodiments of the present disclosure include a non-transitory computer-readable medium with computer-executable instructions stored thereon executed by one or more processors to perform a method to select and implement a neural network for an embedded system. The method includes selecting a neural...

Full description

Saved in:
Bibliographic Details
Main Authors SAVVIDES Marios, SINGH Karanhaar, ADLER Gavriel, NEBLETT Kyle, MATTY John, LIN An Pang, THANIKKAL Ajmal, VENUGOPALAN Shreyas
Format Patent
LanguageEnglish
Published 22.02.2018
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Embodiments of the present disclosure include a non-transitory computer-readable medium with computer-executable instructions stored thereon executed by one or more processors to perform a method to select and implement a neural network for an embedded system. The method includes selecting a neural network from a library of neural networks based on one or more parameters of the embedded system, the one or more parameters constraining the selection of the neural network. The method also includes training the neural network using a dataset. The method further includes compressing the neural network for implementation on the embedded system, wherein compressing the neural network comprises adjusting at least one float of the neural network.
Bibliography:Application Number: US201715679926