Artificial Neural Networks: A Tutorial
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Hi-index | 0.00 |
In this paper, an emerging artificial neural network (ECANN) is proposed. Abstracting from a latest research in neuroscience, electromagnetic coupling among neuron activities is introduced into the model. Besides, the overall network can be viewed as a system with physical significance of circuitry, and each neuron is presented as differential equation. At the mean time, the spatial grid topology is employed in order to develop its parallelism. This artificial neural network is designed for fitting and predicting dynamic data, and has successfully worked in simulation part of this paper.