초록 ▼

A system for building an artificial neural network is provided which precisely defines the network's structure of artificial neurons, and non-iteratively determines the synapse-weights and hard limiter threshold of each artificial neuron of the network. The system includes a computer for analyzing i

A system for building an artificial neural network is provided which precisely defines the network's structure of artificial neurons, and non-iteratively determines the synapse-weights and hard limiter threshold of each artificial neuron of the network. The system includes a computer for analyzing input data, which represents patterns of different classes of signals, to generate one or more data points in two or three dimensions representative of the signals in each of the different classes. A distribution of the data points is visualized on a map on an output device coupled to the computer. The data points are clustered on the map into clusters in accordance with the classes associated with the data points, and the map is then partitioned into regions by defining linear boundaries between clusters. The artificial neural network is configured in accordance with the data points, clusters, boundaries, and regions, such that each boundary represents a different artificial neuron of the artificial neural network, and the geometric relationship of the regions on the map to the classes defines the logic connectivity of the artificial neurons. The synaptic weights and threshold of each artificial neuron in the network are graphically determined based on the data points of the map.

대표청구항 ▼

[ What is claimed is:] [1.] A system for building an artificial neural network of artificial neurons on a computer interactively with a user using input data representing patterns of different classes of signals comprising:means for analyzing said input data to generate one or more data points in at

[ What is claimed is:] [1.] A system for building an artificial neural network of artificial neurons on a computer interactively with a user using input data representing patterns of different classes of signals comprising:means for analyzing said input data to generate one or more data points in at least two dimensions representative of said signals in each of said different classes;means for visualizing the distribution of said data points on a map in at least two dimensions using an output device coupled to said computer;means for clustering said data points on said map provided by said visualizing means into clusters in accordance with the classes associated with said data points;means for partitioning said map provided by said visualizing means into regions by defining boundaries between said clusters interactively with the user; andmeans for configuring said artificial neural network in accordance with said data points, said cluster, said boundaries, and said regions, in which each of said boundaries defines a different one of the artificial neurons of said artificial neural network.