Invention Grant
- Patent Title: Architecture for an electrochemical artificial neural network
-
Application No.: US15479814Application Date: 2017-04-05
-
Publication No.: US10748059B2Publication Date: 2020-08-18
- Inventor: Matthew Warren Copel , James Bowler Hannon , Satoshi Oida , John Jacob Yurkas
- 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: McGinn IP Law Group, PLLC
- Agent Vazken Alexanian
- Main IPC: G06N3/063
- IPC: G06N3/063 ; G11C11/54 ; G06N3/08 ; G06N3/04 ; G11C13/00

Abstract:
A resistive element in an electrochemical artificial neural network, includes a transition metal oxide thin film forming a working electrode, a pair of first electrodes connected to the working electrode, and a reference electrode for electrochemical doping of the working electrode. The biasing of the pair of first electrodes with respect to the reference electrode according to a determination of conductivity between the pair of first electrodes controls the resistance of the working electrode.
Public/Granted literature
- US20180293487A1 ARCHITECTURE FOR AN ELECTROCHEMICAL ARTIFICIAL NEURAL NETWORK Public/Granted day:2018-10-11
Information query