Method and apparatus for training and operating a

专利名称：Method and apparatus for training and

operating a neural network for detectingbreast cancer

发明人：Lucas Parra,Paul Sajda,Clay Douglas Spence申请号：US09126341申请日：19980730公开号：US06208983B1公开日：20010327

专利附图：

摘要：A method and apparatus for training and operating a neural network usinggated data. The neural network is a mixture of experts that performs “soft”

partitioning of a network of experts. In a specific embodiment, the technique is used todetect malignancy by analyzing skin surface potential data. In particular, the inventionuses certain patient information, such as menstrual cycle information, to “gate” theexpert output data into particular populations, i.e., the network is soft partitioned intothe populations. An Expectation-Maximization (EM) routine is used to train the neuralnetwork using known patient information, known measured skin potential data andcorrect diagnosis for the particular training data and patient information. Once trained,the neural network parameters are used in a classifier for predicting breast cancermalignancy when given the patient information and skin potentials of other patients.

申请人：SARNOFF CORPORATION

代理人：William J. Burke

更多信息请下载全文后查看