Invention Grant
- Patent Title: Implementation model of self-organizing reservoir based on lorentzian nonlinearity
-
Application No.: US15794203Application Date: 2017-10-26
-
Publication No.: US11295198B2Publication Date: 2022-04-05
- Inventor: Naoki Kanazawa
- 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 PC
- Agent Randall Bluestone
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08

Abstract:
To realize a reservoir computing system in which the reservoir is configured to be suitable for various learning targets, provided is a self-organizing reservoir computing system, including an input layer that outputs an input layer signal corresponding to input data; a reservoir layer that includes therein a nonlinear signal path using physical resonance phenomena and is operable to output an inherent reservoir layer signal in response to the input layer signal; and an output layer that outputs output data corresponding to the reservoir layer signal. Also provided is a self-organizing method.
Public/Granted literature
- US20190130252A1 IMPLEMENTATION MODEL OF SELF-ORGANIZING RESERVOIR BASED ON LORENTZIAN NONLINEARITY Public/Granted day:2019-05-02
Information query