Abstract ** This paper presents a novel fast algorithm for feedforward neural networks training. It is based on the Recursive Least Squares (RLS) method commonly used designing adaptive filters. Besides, it utilizes two techniques of linear algebra, namely orthogonal transformation method, called Givens Rotations (GR), and QR decomposition, creating GQR (symbolically we write GR + = GQR) proced...

in this paper, a new method is presented for the detection of defects in random textures. in the training stage, the feature vectors of the normal textures’ images are extracted by using the optimal response of gabor wavelet filters, and their probability density is estimated by means of the gaussian mixture model (gmm). in the testing stage, similar to the previous stage,at  first, the feature...

Artificial neural networks (ANNs), one of the most important artificial intelligence techniques, are used extensively in modeling many types problems. A successful training process is required to create effective models with ANN. An algorithm essential for a process. In this study, new network called hybrid bee colony based on scout stage (HABCES) was proposed. The HABCES includes four fundamen...

A novel improvement in neural network training for pattern classification is presented in this paper. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon’s information theory. This algorithm is applicable to artificial neural networks (ANNs) in general, although here it is applied to a multilayer perceptron (MLP). During the training phas...

There has been growing interest in practice in using unlabeled data together with labeled data in machine learning, and a number of different approaches have been developed. However, the assumptions these methods are based on are often quite distinct and not captured by standard theoretical models. In this paper we describe a PAC-style framework that can be used to model many of these assumptio...

In this paper, we first present a self-training semi-supervised support vector machine (SVM) algorithm and its corresponding model selection method, which are designed to train a classifier with small training data. Next, we prove the convergence of this algorithm. Two examples are presented to demonstrate the validity of our algorithm with model selection. Finally, we apply our algorithm to a ...