Self organizing general pattern class separator and identifier
Parallel, multi-unit, adaptive, nonlinear pattern class separator and identifier
Massively parellel real-time network architectures for robots capable of self-calibrating their operating parameters through associative learning
Discrete weight neural network
Adaptive, neural-based signal processor
Neural network with back propagation controlled through an output confidence measure
Digital neural network processing elements
Simple distance neuron
Vector quantization image processing apparatus
Real time adaptive probabilistic neural network system and method for data sorting Patent #: 5276772
ApplicationNo. 008071 filed on 01/22/1993
US Classes:706/25, Learning method706/30, Recurrent706/31, Multilayer feedforward706/38, Analog neural network706/41Digital neural network
ExaminersPrimary: Downs, Robert W.
Attorney, Agent or Firm
International ClassG06F 015/42
AbstractAn artificial neural network incorporating difference type, non-MP (McCullough-Pitts) neuron cells and a method and apparatus for training this network. More specifically, the output of each neuron cell is a nonlinear mapping of a distance metric of a difference vector and an offset. The difference vector is the difference between an input and a reference vector; the offset is representative of the radius of a hyperspheroidal discriminant function.