[특허]Recurrent neural network with variable size intermediate layer

Recurrent neural network with variable size intermediate layer 원문보기

IPC분류정보
국가/구분	United States(US) Patent 등록
국제특허분류(IPC7판)	G06F-015/18
출원번호	US-0727871 (1991-07-10)
우선권정보	JP-0232845 (1988-09-17); JP-0232846 (1988-09-17); JP-0235441 (1988-09-20)
발명자 / 주소	Hiraiwa Atsunobu (Kanagawa JPX)
출원인 / 주소	Sony Corporation (Tokyo JPX 03)
인용정보	피인용 횟수 : 22 인용 특허 : 0

초록 ▼

The present invention is concerned with a signal processing system having a learning function pursuant to the back-propagation learning rule by the neural network, in which the learning rate is dynamically changed as a function of input values to effect high-speed stable learning. The signal processing system of the present invention is so arranged that, by executing signal processing for the input signals by the recurrent network formed by units each corresponding to a neuron, the features of the sequential time series pattern such as voice signals fluctuating on the time axis can be extracted through learning the coupling state of the recurrent network. The present invention is also concerned with a learning processing system adapted to cause the signal processing section formed by a neural network to undergo signal processing pursuant to the back-propagation learning rule, wherein the local minimum state in the course of the learning processing may be avoided by learning the coefficient of coupling strength while simultaneously increasing the number of the unit of the intermediate layer.

대표청구항 ▼

A learning processing system comprising a signal processing section including at least an input layer, an intermediate layer and an output layer, each of said layers being made up of a plurality of signal processing units, and a learning processing section for repeatedly and sequentially computing, from said output layer towards said input layer, a coefficient Wji of coupling strength between said output layer and said intermediate layer and said intermediate layer and said input layer of said signal processing section on the basis of error data dji between an output value of said output layer for input signal patterns entered into said input layer and a predetermined output value denoted as a teacher signal, thereby performing learning processing of said coefficient of coupling strength, wherein control means are provided in said learning processing section for increasing the number of said signal processing units of said intermediate layer, and wherein said learning processing section performs learning processing of said coefficient of coupling strength as said learning processing section causes the number of said signal processing units of said intermediate layer to be increased.

이 특허를 인용한 특허 (22)

Frye Robert Charles ; Harry Thomas Richard ; Lory Earl Ryan ; Rietman Edward Alois, Active neural network control of wafer attributes in a plasma etch process.
상세보기
Tani, Jun, Information processing apparatus and method, and recording medium.
상세보기
Tani,Jun, Information processing apparatus and method, and recording medium.
상세보기
Tani,Jun, Information processing apparatus and method, and recording medium.
상세보기
Tani,Jun, Information processing apparatus and method, and recording medium.
상세보기
Commons, Michael Lamport, Intelligent control with hierarchical stacked neural networks.
상세보기
Coleman, Chadwick M.; VanHall, Richard, Method and system for circular to horizontal transposition of an image.
상세보기
de Vries Aalbert, Method and system for training a neural network with adaptive weight updating and adaptive pruning in principal componen.
상세보기
Higashino Junichi (Tokyo JPX) Persoon Eric H. J. (Eindhoven NLX), Method for adjusting network parameters in a multi-layer perceptron device provided with means for executing the method.
상세보기
Gentric Philippe,FRX ; Minot Joel,FRX, Method for constructing a neural device for classification of objects.
상세보기
Takahashi Isao (Hitachi JPX) Endo Fumihiro (Hitachi JPX) Yamagiwa Tokio (Hitachi JPX), Method of configuring a neural network and a diagnosis/control system using the neural network.
상세보기
Takahashi Isao (Maebashi JPX) Endo Fumihiro (Hitachi JPX) Yamagiwa Tokio (Hitachi JPX), Method of configuring a neural network and a diagnosis/recognition system using the same.
상세보기
Ueda Tomoaki,JPX, Methods and apparatus for estimating unknown quantities.
상세보기
Garner, Bernadette, Neural networks and method for training neural networks.
상세보기
Lo James Ting-Ho, Nonadaptively trained adaptive neural systems.
상세보기
Yoda Fumio, Self-organizing neural network for pattern classification.
상세보기
Baba Kenji,JPX ; Enbutsu Ichiro,JPX ; Watanabe Shoji,JPX ; Yahagi Hayao,JPX ; Maruhashi Fumio,JPX ; Matsuzaki Harumi,JPX ; Matsumoto Hiroshi,JPX ; Nogita Shunsuke,JPX ; Yoda Mikio,JPX ; Hara Naoki,JP, Supporting method and system for process operation.
상세보기
Baba Kenji,JPX ; Enbutsu Ichiro,JPX ; Watanabe Shoji,JPX ; Yahagi Hayao,JPX ; Maruhashi Fumio,JPX ; Matsuzaki Harumi,JPX ; Matsumoto Hiroshi,JPX ; Nogita Shunsuke,JPX ; Yoda Mikio,JPX ; Hara Naoki,JP, Supporting neural network method for process operation.
상세보기
Tascillo Anya Lynn ; Tascillo Mark Anthony, System and method for distinguishing and characterizing motor vehicles for control of automatic drivers.
상세보기
Matsuoka Masahiro,JPX ; Golea Mostefa,AUX, Time-series trend estimating system and method using column-structured recurrent neural network.
상세보기
Nightingale Charles (Felixstowe GB2) Wyard Peter J. (Woodbridge GB2), Trainable neural network having short-term memory for altering input layer topology during training.
상세보기
Kochi Nobuo (Tokyo JPX), Waveform evaluating apparatus using neural network.
상세보기

IPC	Description
A	생활필수품
A62	인명구조; 소방(사다리 E06C)
A62B	인명구조용의 기구, 장치 또는 방법(특히 의료용에 사용되는 밸브 A61M 39/00; 특히 물에서 쓰이는 인명구조 장치 또는 방법 B63C 9/00; 잠수장비 B63C 11/00; 특히 항공기에 쓰는 것, 예. 낙하산, 투출좌석 B64D; 특히 광산에서 쓰이는 구조장치 E21F 11/00)
A62B-1/08	.. 윈치 또는 풀리에 제동기구가 있는 것

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 국가코드, 자료구분, 상태, 출원번호, 출원일자, 공개번호, 공개일자, 등록번호, 등록일자, 발명명칭(한글), 발명명칭(영문), 출원인(한글), 출원인(영문), 출원인코드, 대표IPC 관리번호, 국가코드, 자료구분, 상태, 출원번호, 출원일자, 공개번호, 공개일자, 공고번호, 공고일자, 등록번호, 등록일자, 발명명칭(한글), 발명명칭(영문), 출원인(한글), 출원인(영문), 출원인코드, 대표출원인, 출원인국적, 출원인주소, 발명자, 발명자E, 발명자코드, 발명자주소, 발명자 우편번호, 발명자국적, 대표IPC, IPC코드, 요약, 미국특허분류, 대리인주소, 대리인코드, 대리인(한글), 대리인(영문), 국제공개일자, 국제공개번호, 국제출원일자, 국제출원번호, 우선권, 우선권주장일, 우선권국가, 우선권출원번호, 원출원일자, 원출원번호, 지정국, Citing Patents, Cited Patents
저장형식	Text(ASCII format) Excel format PIAS분석(.xls)
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증

Recurrent neural network with variable size intermediate layer 원문보기

초록 ▼

대표청구항 ▼

연구과제 타임라인

이 특허를 인용한 특허 (22)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Recurrent neural network with variable size intermediate layer 원문보기

초록 ▼

대표청구항 ▼

연구과제 타임라인

전체(0) 논문(0) 특허(0) 보고서(0)

전체(0) 논문(0) 특허(0) 보고서(0)

이 특허를 인용한 특허 (22)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트