Neural networks are broadly used to approximate non-linear functions. However, it is difficult to decide an appropriate structure for a given problem. In this paper, "growing neural network" is proposed as an extension of backpropagation (BP) learning. The propagated error signal is diffused from a target neuron as a substance. The axon of a growing neuron grows according to the concentration gradient of the substance. In a simulation, it was examined that the simplest problems, "AND" and "OR", could be solved by the neural network and 2-layer structure was properly obtained.
展开▼
