CONTINUOUS CONTROL OF ATTENTION FOR A DEEP LEARNING NETWORK

Number of patents in Portfolio can not be more than 2000

United States of America

APP PUB NO 20200026247A1
SERIAL NO

16039934

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network includes initializing a control-value function, an observation-value function and a sequence of states associated with a current episode. If a current epoch associated with the current episode is odd, an observation-action is selected, the observation-action is executed to observe a partial image, and the observation-value function is updated based on the partial image and the control-value function. If the current epoch is even, a control-action is selected, the control-action is executed to obtain a reward corresponding to the control-action, and the control-value function is updated based on the reward and the observation-value function.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
INTERNATIONAL BUSINESS MACHINES CORPORATIONNEW ORCHARD ROAD ARMONK NY 10504

International Classification(s)

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Ohsawa, Shohei Tokyo, JP 13 116
Osogami, Takayuki Kanagawa-ken, JP 107 423

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation