-Since last decade, classification methods are useful in a wide range of applications. Classification is a task to group the sample having similar properties. This capability can be introduced in computer system by designing various types of classifiers. Neural network is one of the artificial intelligent techniques that have many successful examples when applying to this problem. Here, a Binar...

It is known that the N-bit parity problem is solvable by a standard feed-forward neural network having a single hidden layer consisting of (N/2) + 1 hidden units if N is even and (N+1)/2 hidden units if N is odd. The network does not allow a direct connection between the input layer and the output layer and the transfer function used in all hidden units and the output unit is the usual sigmoida...

An optimal artificial neural network (ANN) has been developed to predict the Nusselt number of non-Newtonian nanofluids. The resulting ANN is a multi-layer perceptron with two hidden layers consisting of six and nine neurons, respectively. The tangent sigmoid transfer function is the best for both hidden layers and the linear transfer function is the best transfer function for the output layer....

The Neural Network is a directed graph consists of multiple layers of neurons, which is also referred to as units. In general there is no connection between units of the same layer and there are only connections between adjacent layers. The first layer is the input and is referred to as visible layer v. Above the visible layer there are multiple hidden layers {h1, h2, ..., hn}. And the output o...

A two-layer neural network can be used to approximate any nonlinear function. T h e behavior of the hidden nodes tha t allows the network to do this is described. Networks w i th one input are analyzed first, and the analysis is then extended to networks w i t h mult iple inputs. T h e result of th is analysis is used to formulate a method for ini t ial izat ion o f the weights o f neural netwo...

The output weight optimization-hidden weight optimization (OWO-HWO) algorithm for training the multilayer perceptron alternately updates the output weights and the hidden weights. This layer-by-layer training strategy greatly improves convergence speed. However, in HWO, the desired net function actually evolves in the gradient direction, which inevitably reduces efficiency. In this paper, two i...

Multilayer perceptrons with hard-limiting (signum) activation functions can form complex decision regions. It is well known that a three-layer perceptron (two hidden layers) can form arbitrary disjoint decision regions and a two-layer perceptron (one hidden layer) can form single convex decision regions. This paper further proves that single hidden layer feedforward neural networks (SLFN's) wit...

The use of a proposed recurrent neural network control system to control a four-legged walking robot is presented in this paper. The control system consists of a neural controller, a standard PD controller, and the walking robot. The robot is a planar four-legged walking robot. The proposed Neural Network (NN) is employed as an inverse controller of the robot. The NN has three layers, which are...

The use of a proposed recurrent hybrid neural network to control of walking robot with four legs is investigated in this paper. A neural networks based control system is utilized to the control of four-legged walking robot. The control system consists of four proposed neural controllers, four standard PD controllers and four-legged planar walking robot. The proposed neural network (NN) is emplo...

In this paper, vapor pressure for pure compounds is estimated using the Artificial Neural Networks and a simple Group Contribution Method (ANN–GCM). For model comprehensiveness, materials were chosen from various families. Most of materials are from 12 families. Vapor pressure data of 100 compounds is used to train, validate and test the ANN-GCM model. Va...