Growing Layers of Perceptrons : Introducing the Extentron Algorithm

The ideas presented here are based on two observations of perceptrons: (1) when the perceptron learning algorithm cycles among hyperplanes, the hyperplanes may be compared to select one that gives a best split of the examples, and (2) it is always possible for the perceptron to build a hyper-plane that separates at least one example from all the rest. We describe the Extentron which grows multi-layer networks capable of distinguishing non-linearly-separable data using the simple perceptron rule for linear threshold units. The resulting algorithm is simple, very fast, scales well to large problems , retains the convergence properties of the per-ceptron, and can be completely specied using only two parameters. Results are presented comparing the Extentron to other neural network paradigms and to symbolic learning systems.