Title :
A novel, geometric supervised learning scheme using linear programming approach
Abstract :
Based on a novel formulation of a two-layer, feedforward, artificial neural network that has hard-limited neuron response functions, the supervised learning problem of finding the connection matrix [aij] in terms of the required input-output mapping is viewed as an N-dimensional geometric problem. The solution of this geometric problem can be obtained by means of a generalized simplex method used in linear programming. Under a generalized feasibility criterion, [aij] is then solved uniquely. The method used is a one-step solve-all method instead of the conventional iterative, step-by-step method. The formulation and the solution of this geometric problem are discussed in detail, and numerical examples verifying the theoretical predictions are given
Keywords :
learning systems; linear programming; neural nets; artificial neural network; connection matrix; feasibility criterion; feedforward neural network; geometric learning; hard-limited neuron response functions; input-output mapping; linear programming; one-step solve-all method; simplex method; supervised learning; two layer neural network;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137861