Processing

Please wait...

Settings

Settings

Goto Application

1. JP2014013581 - AUTONOMOUS LEARNING TOOL BASED ON BIOLOGY

Office
Japan
Application Number 2013167819
Application Date 12.08.2013
Publication Number 2014013581
Publication Date 23.01.2014
Grant Number 5732495
Grant Date 17.04.2015
Publication Kind B2
IPC
G06N 3/02
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
G05B 13/02
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
G06N 5/02
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
G06N 99/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
H01L 21/02
HELECTRICITY
01BASIC ELECTRIC ELEMENTS
LSEMICONDUCTOR DEVICES; ELECTRIC SOLID STATE DEVICES NOT OTHERWISE PROVIDED FOR
21Processes or apparatus specially adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
02Manufacture or treatment of semiconductor devices or of parts thereof
CPC
G05B 13/0265
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0265the criterion being a learning criterion
G06N 5/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
04Inference methods or devices
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 5/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
Applicants TOKYO ELECTRON LTD
東京エレクトロン株式会社
Inventors SANJEEV KAUSHAL
コーシャル、サンジーブ
PATEL SUKESH JANUBHAI
パテル、スケシュ・ジャヌブハイ
SUGIJIMA KENJI
杉島 賢次
Agents 特許業務法人スズエ国際特許事務所
河野 哲
村松 貞男
鈴江 正二
Priority Data 12044958 08.03.2008 US
Title
(EN) AUTONOMOUS LEARNING TOOL BASED ON BIOLOGY
(JA) 生物学に基づく自律学習ツール
Abstract
(EN)

PROBLEM TO BE SOLVED: To provide an autonomous learning tool system based on biology and a method to be used for learning and analysis by the system.

SOLUTION: An autonomous learning tool system includes: one or more tool systems; an interaction manager; and an autonomous learning system based on a biological learning principle. The tool system executes a set of specific tasks, and generates an asset and data related to the asset, and characterizes various processes and the performance of a related tool. The interaction manager receives and formats the data. The system includes a memory platform and a processing platform. Each platform is recursively defined, and communicates via a network. Knowledge generated and accumulated in the autonomous learning system related to an autonomous tool can be cast in a semantic network. The semantic network may be used for learning and developing the target of the tool on the basis of context.

COPYRIGHT: (C)2014,JPO&INPIT

(JA)

【課題】生物学に基づく自律学習ツールシステムと、システムが学習と分析とに用いる方法とを提供する。
【解決手段】自律学習ツールシステムは、1つ以上のツールシステムと、相互作用マネージャと、生物学的な学習原理に基づく自律学習システムとを含む。ツールシステムは、特定のタスクのセットを実行して、アセットと、アセットに関するデータとを生成し、様々なプロセス及び関連するツールの性能を特徴付ける。相互作用マネージャは、データを受信して、フォーマットする。システムは、メモリプラットフォームと処理プラットフォームとを含む。各プラットフォームは、再帰的に定義され、ネットワークを通して通信する。自律ツールに関連する自律学習システムにおいて生成され蓄積された知識は、意味ネットワークにキャストすることができる。意味ネットワークは、コンテキストに基づいてツールの目標を学習して進めるために用いられ得る。
【選択図】図1