Unsupervised neural network classification with back propagation
Patent 5590218 Issued on December 31, 1996. Estimated Expiration Date: 
June 7, 2015. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.
June 7, 2015. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.Patent ReferencesMethod and apparatus for learning in a neural network Method and apparatus for diagnosis of breast tumors Method and apparatus for determining and organizing feature vectors for neural network recognition Neural network apparatus Patent #: 5283838 InventorAssigneeApplicationNo. 481108 filed on 06/07/1995US Classes:382/157, Network learning techniques (e.g., back propagation)128/925, Neural network706/20, Classification or recognition706/25Learning methodExaminersPrimary: Mancuso, JosephAssistant: Patel, Rajnikant B. Attorney, Agent or FirmInternational ClassG06K 009/62AbstractAn 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 converge on a stable classification, thereby providing unsupervised back propagation. In a further embodiment, samples classified with the trained network may serve as the training sets for additional subdivisions to grow additional layers of a hierarchical classification tree which converges to indivisible branch tips. After training is completed, such a tree may be used to classify new unlabelled samples with high efficiency. In yet another embodiment, the unsupervised back propagation method of the present invention may be adapted to classify fuzzy sets.Other References
Field of SearchNetwork learning techniques (e.g., back propagation) | |
