The Go-Back-N and Selective-Repeat automatic repeat request (ARQ) protocols are widely used for error control in computer-communication networks. They are nearly optimal for channels characterized by low error rates and small propagation delays, and thus suitable for many classical data transmission applications. However, these protocols are not eecient for modern non-conventional channels with...

In this paper we propose a novel bio-inspired model of a mobile robot navigation system. The novelty of our work consists in combining short term memory and online neural network learning using history of events stored in this memory. The neural network is trained with a modified error back propagation algorithm that utilizes reward and punishment principal while interacting with the environment.

An intrusion detection system (IDS) inspects all inbound and outbound network activity and identifies suspicious patterns that may indicate a network or system attack from someone attempting to break into or compromise a system. Soft computing techniques resemble biological processes more closely than traditional techniques, which are largely based on formal logical systems. Knowledge Discovery...

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a nonlinear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back...

In this paper, adaptive learning algorithms to obtain better generalization performance are proposed. We speci"cally designed cost terms for the additional functionality based on the "rstand second-order derivatives of neural activation at hidden layers. In the course of training, these additional cost functions penalize the input-to-output mapping sensitivity and highfrequency components in tr...

Two schemes to obtain phonemic transcriptions of spoken utterances are described and compared. Both schemes utilize the so called Self-Organizing Kohonen Maps first to vector quantize speech into a sequence of phoneme Iabels centisecond apart. In the original scheme, this quasiphoneme sequence is converted into a phoneme string with simple durational transformation rules. In the scheme introduc...

This paper proposes a neural network approach based on Error Back Propagation (EBP) for classification of different eye images. To reduce the complexity of layered neural network the dimensions of input vectors are optimized using Singular Value Decomposition (SVD). The main objective of this work is to prove usefulness of SVD to form a compact set of features for classification by EBP algorith...

consecutive droughts in sistan and baloochestan province cause water resources restriction and this isa very significant problem for this region. in this study, in order to forecast the drought cycle in 9climatological stations in the province, we used artificial neural networks. the input data wereaverage of annual rainfall data in all stations and also deciles precipitation index, which the f...

In this paper we present the implementation of Error Back Propagation Training Algorithm (EBPT) in VHSIC Hardware Descriptive Language (VHDL) platform for two standard benchmark problems of Nonlinear Classification of XOR function and Sine wave Generation. The effect of variation of learning parameters on accuracy of the output and speed of convergence of the algorithm are presented. Improved s...

A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this netwo...