LINEARLY AUGMENTED NEURAL NETWORK

A neural network is structured to connect the input values of an input set, at each level, to that level's output using a linear bypass connection. The linear bypass connection passes the input values, to the output, without applying a non-linear function to them.

Saved in:
Bibliographic Details
Main Authors Ghahremani Pegah, Droppo James G, Seltzer Michael L
Format Patent
LanguageEnglish
Published 29.06.2017
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A neural network is structured to connect the input values of an input set, at each level, to that level's output using a linear bypass connection. The linear bypass connection passes the input values, to the output, without applying a non-linear function to them.
Bibliography:Application Number: US201514980976