METHOD AND APPARATUS FOR IMPROVING RESILIENCE IN CUSTOMIZED PROGRAM LEARNING NETWORK COMPUTATIONAL ENVIRONMENTS

An apparatus and a method are provided for learning a program with a large number of parameters. In one embodiment, a method not only distorts the input values, but also distorts some of the parameters in the program model. Such an approach not only forces the learned program to acquire parameter va...

Full description

Saved in:
Bibliographic Details
Main Author HARIK GEORGES
Format Patent
LanguageEnglish
Published 05.06.2014
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An apparatus and a method are provided for learning a program with a large number of parameters. In one embodiment, a method not only distorts the input values, but also distorts some of the parameters in the program model. Such an approach not only forces the learned program to acquire parameter values to predict missing or desired data, but also to correct errors in the input data and the program parameters themselves, thereby rendering the learned program more resilient to overfitting and falling into local optima.
Bibliography:Application Number: US201313921124