Modern recognition systems require high-accuracy low-complexity methods. We explore a polynomial network approach to recognition problems. Traditionally, polynomial networks have been difficult to use for recognition because of either low accuracy or problems associated with large training sets. We detail a new training method that solves these problems. For identification, the method partition...

In this work we will propose an acceleration procedure for the Mitchell–Demyanov–Malozemov (MDM) algorithm (a fast geometric algorithm for SVM construction) that may yield quite large training savings. While decomposition algorithms such as SVMLight or SMO are usually the SVM methods of choice, we shall show that there is a relationship between SMO and MDM that suggests that, at least in their ...

We consider deep neural networks, in which the output of each node is a quadratic function of its inputs. Similar to other deep architectures, these networks can compactly represent any function on a finite training set. The main goal of this paper is the derivation of an efficient layer-by-layer algorithm for training such networks, which we denote as the Basis Learner. The algorithm is a univ...

This study presents a new hybrid algorithm for training RBF network. The algorithm consists of a proposed clustering algorithm to position the RBF centres and Givens least squares to estimate the weights. This paper begins with a discussion about the problems of clustering for positioning RBF centres. Then a clustering algorithm called moving k-means clustering algorithm was proposed to reduce ...

The deep learning or deep neural network (DNN) currently provide the best solution to many problems in classification. However, DNN requires much more time and many calculations than existing other classification algorithms. In addition, if new features and classes are added into existing model, it should re-learn all of data set in order to apply the new features and classes into learned model...

Radial Basis Function Neural Networks (RBF NNs) are one of the most applicable NNs in the classification of real targets. Despite the use of recursive methods and gradient descent for training RBF NNs, classification improper accuracy, failing to local minimum and low-convergence speed are defects of this type of network. In order to overcome these defects, heuristic and meta-heuristic algorith...

The main goal of this paper is to present a new learning algorithm which has been applied to feedforward neural networks. It was used not only during the learning phase of the network, but also to optimise the number of hidden neurons. This learning algorithm is inspired on the classical backpropagation algorithm but it owns some variations due to kind of network used. This algorithm was applie...

Neural networks have been proven to be very successful in many cases where other traditional techniques failed to give satisfactory results. Despite their popularity, several problems exist. Even with the adequate network architecture, frustrating problems of correct choice of initial weights for given architecture remain. The proposed method uses combination of approaches used in genetic algor...

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either...

Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon...