[특허]Method and apparatus for training a neural network using evolutionary programming

Method and apparatus for training a neural network using evolutionary programming 원문보기

IPC분류정보
국가/구분	United States(US) Patent 등록
국제특허분류(IPC7판)	G06F-015/18
출원번호	US-0716687 (1991-06-17)
발명자 / 주소	Fogel David B. (San Diego CA) Fogel Lawrence J. (La Jolla CA)
출원인 / 주소	Orincon Corporation (San Diego CA 02)
인용정보	피인용 횟수 : 24 인용 특허 : 0

초록 ▼

A method and apparatus for training neural networks using evolutionary programming. A network is adjusted to operate in a weighted configuration defined by a set of weight values and a plurality of training patterns are input to the network to generate evaluations of the training patterns as network outputs. Each evaluation is compared to a desired output to obtain a corresponding error. From all of the errors, an overall error value corresponding to the set of weight values is determined. The above steps are repeated with different weighted configurations to obtain a plurality of overall error values. Then, for each set of weight values, a score is determined by selecting error comparison values from a predetermined variable probability distribution and comparing them to the corresponding overall error value. A predetermined number of the sets of weight values determined to have the best scores are selected and copies are made. The copies are mutated by adding random numbers to their weights and the above steps are repeated with the best sets and the mutated copies defining the weighted configurations. This procedure is repeated until the overall error values diminish to below an acceptable threshold. The random numbers added to the weight values of copies are obtained from a continuous random distribution of numbers having zero mean and variance determined such that it would be expected to converge to zero as the different sets of weight values in successive iterations converge toward sets of weight values yielding the desired neural network performance.

대표청구항 ▼

A neural network training apparatus, comprising: (a) a plurality of neural networks each capable of receiving data and operative in a plurality of different weighted configurations, each configuration defined by a different set of weight values; (b) means for adjusting each network to operate in different weighted configurations defined by a corresponding different set of weight values; (c) means, responsive to an application of a plurality of training patterns to each of the networks, for generating respective evaluations of the training patterns from each of the networks as outputs of the networks; (d) means for comparing the evaluations of the training patterns to corresponding desired outputs of the networks to obtain corresponding errors; (e) means for determining from all of the errors obtained from said comparing means overall error values corresponding to the sets of weight values; (f) for each of said sets of weight values, means for determining a score by selecting respective error comparison values from a predetermined variable probability distribution and comparing thereto the corresponding overall error value; (g) means for selecting a predetermined number of the sets of weight values determined to have the best scores; (h) means for generating copies of the sets of weight values selected by said selecting means; (i) means for generating, for each weight value of the copies generated by said means for generating copies, a corresponding random number from a continuous random distribution of numbers having a mean of zero and a variance which is a function of the overall error value determined by said overall error generating means for the set of weight values from which the copy which includes said each weight value was generated; and (j) means for mutating the weight values of the copies by adding the corresponding random numbers thereto to create new sets of weight values, said means for adjusting including means for replacing some of the weighted configurations of said network with new weighted configurations based on said new sets of weight values.

이 특허를 인용한 특허 (24)

Melamed Benjamin ; Jelenkovic Predrag, Algorithmic modeling of TES processes for simulation analysis.
상세보기
Raichelgauz, Igal; Odinaev, Karina; Zeevi, Yehoshua Y, Apparatus and method for determining user attention using a deep-content-classification (DCC) system.
상세보기
Halper, Steven C.; Wilson, Constance A.; Hourigan, Stephen M., Automated loan risk assessment system and method.
상세보기
Halper, Steven C.; Wilson, Constance A.; Hourigan, Stephen M., Automated loan risk assessment system and method.
상세보기
Halper, Steven C.; Wilson, Constance A.; Hourigan, Stephen M., Automated loan risk assessment system and method.
상세보기
Forman, George Henry; Suermondt, Henri Jacques; Kirshenbaum, Evan Randy, Count estimation via machine learning.
상세보기
Shustorovich Alexander, Evidential confidence measure and rejection technique for use in a neural network based optical character recognition s.
상세보기
Szathmary, Eors; Szatmary, Zoltan; Ittzes, Peter; Szamado, Szabolcs, Evolutionary neural network and method of generating an evolutionary neural network.
상세보기
Keith E. Mathias ; Murali Mani ; J. David Schaffer, Image classification using evolved parameters.
상세보기
Sutton Richard S., Method and apparatus for machine learning.
상세보기
Ramin C. Nakisa GB, Method and apparatus to model the variables of a data set.
상세보기
Coleman, Chadwick M.; VanHall, Richard, Method and system for circular to horizontal transposition of an image.
상세보기
Black Christopher Lee, Method and system for training an artificial neural network.
상세보기
Tewari Ashutosh ; Narayan Perinchery, Method for diagnosing and staging prostate cancer.
상세보기
Mathias, Keith E.; Eshelman, Larry J.; Schaffer, J. David, Method for improving neural network architectures using evolutionary algorithms.
상세보기
Ayala,Francisco J., Method, system and computer program for developing cortical algorithms.
상세보기
Gunawardena, Dinan; Vojnović, Milan; Cruise, Richard James; Marbach, Peter, Ranking and suggesting candidate objects.
상세보기
Omatsu, Shigeru; Mitsukura, Yasue; Fukumi, Minoru; Mitsukura, Kensuke; Kita, Koji; Kugo, Kouichi, Region detecting method and region detecting apparatus.
상세보기
Castelaz Patrick F. (Yorba Linda CA), Self organizing adaptive replicate (SOAR).
상세보기
Raichelgauz, Igal; Odinaev, Karina; Zeevi, Yehoshua Y, System and method for creating user profiles based on multimedia content.
상세보기
Ayala,Francisco J., System and method for developing artificial intelligence.
상세보기
Feldgajer Oleg,CAX, System and method for dynamic learning control in genetically enhanced back-propagation neural networks.
상세보기
Raichelgauz, Igal; Odinaev, Karina; Zeevi, Yehoshua Y., System and method for generation of concept structures based on sub-concepts.
상세보기
Keller Steven A. (Coral Springs FL) Lo Jiann-Chang (Boca Raton FL) Mahlbacher James C. (Lake Worth FL), Test sequence optimization process for a circuit tester.
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

Method and apparatus for training a neural network using evolutionary programming 원문보기

초록 ▼

대표청구항 ▼

연구과제 타임라인

이 특허를 인용한 특허 (24)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트

연합인증

Method and apparatus for training a neural network using evolutionary programming 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 (24)

관련 콘텐츠

특허 원문 보기

IPC 상위 출원인

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

선택된 텍스트