Special neural network architectures for easy electronic implementations

Abstract

An overview of various neural network architectures is presented. Depending on applications some of these architectures are capable to perform very complex operations with limited number of neurons, while other architectures, which use more neurons, are easy to train. There are neural network architectures which have very limited requirements for training or no training is required. The importance of the proper learning algorithm was emphasized because with advanced learning algorithm we can train these networks, which cannot be trained with simple algorithms. When simple training algorithms, such as EBP are used, neural networks with larger number of neurons must be used to fulfill the task.