Site Loader
Get a Quote

The complex relationship between the input and output of any process correlation irrespective of the physical features of the system can be done by artificial neural network (ANN). The genetic algorithm (GA) can be applied to ANN for determination and optimization of the ANN parameters. Today, ANNs are recognized as an excellent choice or solving types of complex adsorption problems. In addition, it has popular application to foresee in the adsorption equilibrium of solid-gas or liquid system.
Neural networks are generally formed from a number of inter-connected processing elements or neurons. How the inter-neuron connections are arranged and the structure of a network is determined by the nature of the connection. How the strengths of the connections are made appropriate or trained to obtain a desired general behavior of the network is controlled by its learning algorithm.
Neural networks can be divided according to their structures and learning algorithms. On the basis of their structures, neural networks van divided into two types: feed forward networks and recurrent network. MLPs (multi-layer perceptron) are maybe the best known types of feed forward networks. MLP has three layers: an input layer, an output layer, and an intermediate or hidden layer.
Two most important types of learning algorithms train neural network: supervised and unsupervised learning algorithm. A supervised learning algorithm makes appropriate the strengths or weights of the inter-neuron connections according to the difference between the desired and real network outputs related to given input. An example of supervised learning algorithms is back propagation algorithm. Genetic algorithm is one of the learning algorithms acceptable for training MLPs.

Post Author: admin