[특허]Neural network with normalized learning constant for high-speed stable learning

Neural network with normalized learning constant for high-speed stable learning 원문보기

IPC분류정보
국가/구분	United States(US) Patent 등록
국제특허분류(IPC7판)	G06F-015/18
출원번호	US-0406733 (1989-09-13)
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 : 25 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 modifies the prior art weight change algorithm Dji(n+1)=hdpi.+aji(n) into Dji(n+1)=hbapjOpi)+aji(n) where bj=1/(SiOpi2+1) is used to normalize the learning constant.

대표청구항 ▼

A signal 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 each of said signal processing units 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 value denoted as a teacher signal, thereby performing learning processing of said coefficient Wji of coupling strength, wherein said learning processing section includes means for computing a variant Dji of said coefficient Wji of coupling strength on the basis of hbdpjㆍOpi), where hpi stands for values of inputs in each of said signal processing units, and where bji of coupling strength Wji=Wji+Dji to each of said signal processing units of said signal processing section, said learning processing section performing said learning processing of said coefficient Wji of coupling strength at a learning rate in which said learning constant hb1/Opi2+1).

이 특허를 인용한 특허 (25)

Francisco Jose Ayala, Adaptive neural learning system.
상세보기
Doris M. Ecker ; Lei Duan ; Alexander M. Franz ; Keiko Horiguchi, Analyzing inflectional morphology in a spoken language translation system.
상세보기
Song, In Chul; Choi, Young Sang; Na, Hwi Dong, Apparatus and method for normalizing input data of acoustic model and speech recognition apparatus.
상세보기
Duong, Tuan A., Artificial neural network with hardware training and hardware refresh.
상세보기
Christensen Alan K. ; Broadbent Christopher F., Audio diagnostic system and method using frequency spectrum and neural network.
상세보기
Miyazawa Yasunaga,JPX ; Inazumi Mitsuhiro,JPX ; Hasegawa Hiroshi,JPX ; Edatsune Isao,JPX ; Urano Osamu,JPX, Bifurcated speaker specific and non-speaker specific speech recognition method and apparatus.
상세보기
Bryant Steven M. (Holley NY) Loewenthal Kenneth H. (Rochester NY), High speed segmented neural network and fabrication method.
상세보기
Komori Yasuhiro (Kyoto JPX) Sagayama Shigeki (Kyoto JPX), Learning method of neural network.
상세보기
Higashino Junichi (Kodaira JPX) Kawasaki Kazuhiko (Yokohama JPX) Hara Miyuki (Yokohama JPX), Learning system and a learning pattern showing method for a neural network.
상세보기
Chen Ruxin ; Tanaka Miyuki ; Wu Duanpei ; Olorenshaw Lex S., Method and apparatus for a parameter sharing speech recognition system.
상세보기
Franz Alexander M. ; Horiguchi Keiko, Method and apparatus for adaptive speech recognition hypothesis construction and selection in a spoken language translation system.
상세보기
Horiguchi Keiko ; Franz Alexander M., Method and apparatus for interactive source language expression recognition and alternative hypothesis presentation and selection.
상세보기
Duan Lei ; Franz Alexander M., Method and apparatus for parsing in a spoken language translation system.
상세보기
Alexander M. Franz ; Keiko Horiguchi ; Lei Duan ; Doris M. Ecker, Method and apparatus for performing spoken language translation.
상세보기
Horiguchi Keiko ; Franz Alexander M., Method and apparatus for providing syntactic analysis and data structure for translation knowledge in example-based language translation.
상세보기
Keiko Horiguchi ; Alexander M. Franz, Method and apparatus for style control in natural language generation.
상세보기
Franz Alexander M. ; Horiguchi Keiko, Method and portable apparatus for performing spoken language translation.
상세보기
Coleman, Chadwick M.; VanHall, Richard, Method and system for circular to horizontal transposition of an image.
상세보기
Ayala,Francisco J., Method, system and computer program for developing cortical algorithms.
상세보기
Toomarian Nikzad ; Barhen Jacob, Neural network training by integration of adjoint systems of equations forward in time.
상세보기
Furuta Toshiyuki (Yokohama JPX) Horiguchi Hiroyuki (Yokohama JPX) Eguchi Hirotoshi (Yokohama JPX) Ebi Yutaka (Yokohama JPX) Furukawa Tatsuya (Yokohama JPX) Watanabe Yoshio (Kawasaki JPX) Tsukagoshi T, Neuron unit, neural network and signal processing method.
상세보기
Inazumi Mitsuhiro,JPX, Recognition apparatus using neural network, and learning method therefor.
상세보기
Wu Duanpei ; Tanaka Miyuki ; Amador-Hernandez Mariscela, Speech detection with noise suppression based on principal components analysis.
상세보기
Ayala,Francisco J., System and method for developing artificial intelligence.
상세보기
Tascillo Anya Lynn ; Tascillo Mark Anthony, System and method for distinguishing and characterizing motor vehicles for control of automatic drivers.
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

Neural network with normalized learning constant for high-speed stable learning 원문보기

초록 ▼

대표청구항 ▼

연구과제 타임라인

이 특허를 인용한 특허 (25)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Neural network with normalized learning constant for high-speed stable learning 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 (25)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트