| 摘要 |
<p>A system for building an artificial neural network (62) is provided which precisely defines the network's structure of artificial neurons (78), 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. The data points are clustered on the map (64) into clusters (74, 75) in accordance with the classes associated with the data points, and the map (64) is partitioned into regions by defining linear boundaries between clusters (74, 75). The artificial neural network (62) is configured in accordance with the data points, clusters, boundaries, and regions, such that each boundary represents a different artificial neuron (78) of the artificial neural network (62), and the geometric relationship of the regions on the map to the classes defines the logic connectivity of the artificial neurons (78). The synaptic weights and threshold of each artificial neuron (78) in the network (62) are graphically determined based on the data points of the map (64).</p> |
