This paper presents a new method for training multi-layer perceptron networks called DMP1 (Dynamic Multi-layer Perceptron 1). The method is based upon a divide and conquer approach which builds networks in the form of binary trees, dynamically allocating nodes and layers as needed. The individual nodes of the network are trained using a gentetic algorithm. The method is capable of handling real...

The Recursive Deterministic Perceptron (RDP) feed-forward multilayer neural network is a generalisation of the single layer perceptron topology. This model is capable of solving any two-class classification problem as opposed to the single layer perceptron which can only solve classification problems dealing with linearly separable sets. For all classification problems, the construction of an R...

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e. having more units than the student. It is shown that this is the same as using training data corrupted by Gaussian noise. Each machine is considered in the hi...

Neural network models have been used extensively to model perceptual learning and the effects of discrimination training on generalization, as well as to explore natural classification mechanisms. Here we assess the ability of existing models to account for the time course of generalization shifts that occur when individuals learn to distinguish sounds. A set of simulations demonstrates that co...

This paper analyzes the behavior of a variety of tracking algorithms for single layer threshold networks in the presence of random drift. We use a system identiication model to model a target network where weights slowly change and a tracking network. Tracking algorithms are divided into conservative and nonconservative algorithms. For a random drift rate of , we nd upper bounds for the general...

This paper finds upper bounds for the generalization error of three tracking algorithms when confronted with a worst case adversary. A system identification model is used where both the target and tracking network are single layer threshold networks, with the target weights changing slowly (the drift problem). Previous work considered random unbiased drifting adversaries. This paper focuses on ...

ÐStructuralization of the covariance matrix reduces the number of parameters to be estimated from the training data and does not affect an increase in the generalization error asymptotically as both the number of dimensions and training sample size grow. A method to benefit from approximately correct assumptions about the first order tree dependence between components of the feature vector is p...

This paper presents an investigation into classifying myoelectric signals using a new fuzzy clustering neural network architecture for control of multifunction prostheses. Moreover, a comparative study of the classification accuracy of myoelectric signals using multi-layer perceptron with back-propagation algorithm, and the new fuzzy clustering neural network (FCNN) is presented. The myoelectri...

In this paper an incident response approach is proposed for handling detections of authentication failures in systems that employ dynamic biometric authentication and more specifically keystroke user recognition. The main component of the approach is a multi layer perceptron focusing on the age classification of a user. Empirical findings show that the classifier can detect the age of the subje...

This paper discusses a method for training multi-layer perceptron networks called DMP2 (Dynamic Multi-layer Perceptron 2). The method is based upon a divide and conquer approach which builds networks in the form of binary trees, dynamically allocating nodes and layers as needed. The focus of this paper is on the effects of using multiple node types within the DMP framework. Simulation results s...