Invention Grant
- Patent Title: Battery-based neural network weights
-
Application No.: US15452167Application Date: 2017-03-07
-
Publication No.: US10943169B2Publication Date: 2021-03-09
- Inventor: Stephen W. Bedell , Joel P. De Souza , Yun Seog Lee , Ning Li , Devendra K. Sadana
- Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Applicant Address: US NY Armonk
- Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee Address: US NY Armonk
- Agency: Tutunjian & Bitetto, P.C.
- Agent Kristofer Haggerty
- Main IPC: G06N3/063
- IPC: G06N3/063 ; G06N3/08 ; H01M10/00 ; H01M10/0525 ; H01M2/20

Abstract:
A controllable resistive element and method of forming the same include a state device configured to provide a voltage-controlled resistance responsive to a voltage input. A dielectric layer is formed directly on the state device. A battery is formed directly on the dielectric layer, configured to apply a voltage to the state device based on a charge stored in the battery. A write device is configured to charge the battery responsive to a write signal. An erase device is configured to discharge the battery responsive to an erase signal.
Public/Granted literature
- US20180260694A1 BATTERY-BASED NEURAL NETWORK WEIGHTS Public/Granted day:2018-09-13
Information query