$\require{mediawiki-texvc}$
  • 검색어에 아래의 연산자를 사용하시면 더 정확한 검색결과를 얻을 수 있습니다.
  • 검색연산자
검색연산자 기능 검색시 예
() 우선순위가 가장 높은 연산자 예1) (나노 (기계 | machine))
공백 두 개의 검색어(식)을 모두 포함하고 있는 문서 검색 예1) (나노 기계)
예2) 나노 장영실
| 두 개의 검색어(식) 중 하나 이상 포함하고 있는 문서 검색 예1) (줄기세포 | 면역)
예2) 줄기세포 | 장영실
! NOT 이후에 있는 검색어가 포함된 문서는 제외 예1) (황금 !백금)
예2) !image
* 검색어의 *란에 0개 이상의 임의의 문자가 포함된 문서 검색 예) semi*
"" 따옴표 내의 구문과 완전히 일치하는 문서만 검색 예) "Transform and Quantization"

특허 상세정보

Unsupervised neural network classification with back propagation

국가/구분 United States(US) Patent 등록
국제특허분류(IPC7판) G06K-009/62   
미국특허분류(USC) 382/157 ; 395/23
출원번호 US-0481108 (1995-06-07)
발명자 / 주소
출원인 / 주소
인용정보 피인용 횟수 : 28  인용 특허 : 0
초록

An unsupervised back propagation method for training neural networks. For a set of inputs, target outputs are assigned l\s and O\s randomly or arbitrarily for a small number of outputs. The learning process is initiated and the convergence of outputs towards targets is monitored. At intervals, the learning is paused, and the values for those targets for the outputs which are converging at a less than average rate, are changed (e.g., 0→1, or 1→0), and the learning is then resumed with the new targets. The process is continuously iterated and the outputs c...

대표
청구항

A method for training a neural network model running on a computer system to generate classifications from a training sample set, said neural network model representing a neural network having an input layer an output layer and at least one hidden layer between the input layer and the output layer wherein each layer includes at least one node and wherein each connection between two nodes of successive layers is characterized by an internal weight, said method comprising the steps of: (a) arbitrarily assigning a numeric label to each training sample signa...

이 특허를 인용한 특허 피인용횟수: 28

  1. Fromherz, Markus P. J.; Jackson, Warren B.. Adaptive constraint problem solving method and system. USP2005036865562.
  2. Ayala,Melvin; Adjoundi,Malek. Artificial neural network design and evaluation tool. USP2009037502763.
  3. Feldhake, Michael J.. Cognitive image filtering. USP2009087577631.
  4. Schmidt, Guenter; Binnig, Gerd; Schoenmeyer, Ralf; Schaepe, Arno. Context driven image mining to generate image-based biomarkers. USP2016019245337.
  5. Schmidt, Guenter; Binnig, Gerd; Schoenmeyer, Ralf; Schaepe, Arno. Context driven image mining to generate image-based biomarkers. USP2013118594410.
  6. Butchart, Kate. Data classifier output interpretation. USP2003056564195.
  7. Kubota, Kazuto; Morita, Chie; Hatano, Hisaaki; Nakase, Akihiko. Data division apparatus, data division method and program. USP2011027882050.
  8. Sathyanarayana, Shashidhar. Display of classifier output and confidence measure in an image. USP2012058175362.
  9. Joseph E. Decker. Identity verification methods. USP2002086430305.
  10. Iverson,David L.. Inductive monitoring system constructed from nominal system data and its use in real-time system monitoring. USP2008067383238.
  11. Neuneier Ralf,DEX ; Zimmermann Hans-Georg,DEX. Method and apparatus for computer-supported generation of at least one artificial training data vector for a neural network. USP2001086282529.
  12. Chiang Wan-Ping ; Cortes Corinna ; Jackel Lawrence David ; Lee William. Method and apparatus for determining the accuracy limit of a learning machine for predicting path performance degradati. USP1998025720003.
  13. Ko Gary Kam-Yuen,CAXITX M4C 5P6. Method and apparatus for non-invasive diagnosis of cardiovascular and related disorders. USP2000106135966.
  14. Ii,David L.; Reitz, II,Elliott D.; Tillotson,Dennis A.. Method and computer program product for producing a pattern recognition training set. USP2006107130776.
  15. Meyer, Franck. Method and device for the generation of a classification tree to unify the supervised and unsupervised approaches, corresponding computer package and storage means. USP2009097584168.
  16. MacCuish, John D.; Nicolaou, Christodoulos A.. Method and system for artificial intelligence directed lead discovery though multi-domain agglomerative clustering. USP2003096625585.
  17. Nicolaou, Christodoulos A.; Kelley, Brian P.; Nutt, Ruth F.; Bassett, Susan I.. Method and system for artificial intelligence directed lead discovery through multi-domain clustering. USP2005066904423.
  18. Lyon Richard F. ; Stafford William. Method for training a statistical classifier with reduced tendency for overfitting. USP1999055903884.
  19. Ayala,Francisco J.. Method, system and computer program for developing cortical algorithms. USP2009027493295.
  20. Streit Roy L.. Neural network architecture for non-Gaussian components of a mixture density function. USP1998015712959.
  21. Lim, Ser Nam; Zheng, Jingjing; Luo, Jiajia; Diwinsky, David Scott. Neural network point cloud generation system. USP20190410262243.
  22. Lim, Ser Nam; Jain, Arpit; Diwinsky, David Scott; Bondugula, Sravanthi. Neural network training image generation system. USP20190410262236.
  23. Vian John L.. Neurocomputing control distribution system. USP2001116317658.
  24. Porter ; III Gilbert B. ; Fan Zhigang ; Roberts ; Jr. Frederick J.. On-line learning for neural net-based character recognition systems. USP1999105966460.
  25. Lee, Shih-Jong J.; Lane, Owsley; Oh, Seho. Online learning method in a decision system. USP2005096941288.
  26. Cohen William W.. Rule induction on large noisy data sets. USP1998025719692.
  27. Luo,Yun. Subclass partitioning in a pattern recognition classifier for controlling deployment of an occupant restraint system. USP2009017483866.
  28. Sirosh Joseph. Unsupervised identification of nonlinear data cluster in multidimensional data. USP2001056226408.