In this paper a new neural network (NN) architecture for data driven prediction of accent labels—perceptual accents and pitch accents—for speech synthesis is presented. Within the proposed NN architecture, gating clusters are applied in a time delay (TD) framework. Gating clusters enable the dynamic adaptation of a network structure depending on the actual input to the NN. In the proposed TD fr...

To reduce the background stemming from multiple scattering events, a neural network (NN) was developed to distinguish single peak light patterns from multiple peak light patterns

Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult. We present an Ensemble Neural Network (Neural-Fusion) solution which compares favorably with other methods. We propose a co-evolutionary system to design Neural Networks Ensemble. This method addresses the issues of automatic determination of the number of...

The use of a new Recurrent Neural Network (RNN) for controlling a robot manipulator is presented in this paper. The RNN is a modification of Elman network. In order to solve load uncertainties, a fast-load adaptive identification is also employed in a control system. The weight parameters of the network are updated using the standard Back-Propagation (BP) learning algorithm. The proposed contro...

This paper presents neural network (NN) control of planar four-legged walking robot. The control system consists of a neural controller, standard PD controller and walking robot. Proposed NN is employed as an inverse controller of the robot. In addition to feedforward connections from the input layer to the hidden layer and from the hidden layer to the output layer, there is also feedback conne...

Traditionally, human activity recognition has been achieved mainly by the statistical pattern recognition techniques such as the Nearest Neighbor Rule (NNR), and the state-space methods, e.g. the Hidden Markov Model (HMM). This paper proposes three novel approaches – the use of the Elman Network (EN) and two hybrids of Neural Network (NN) and HMM, i.e. HMM-NN and NN-HMM, to recognize ten simple...

Electromyograph (EMG) features have the properties of large variations and nonstationarity. An important issue in the classification of EMG is the classifier design. The major goal of this paper is to develop a classifier for the classification of eight kinds of prehensile postures to achieve high classification rate and reduce the online learning time. The cascaded architecture of neural netwo...

This paper evaluates a novel k-nearest neighbour (k-NN) classifier built from binary neural networks. The binary neural approach uses robust encoding to map standard ordinal, categorical and numeric data sets onto a binary neural network. The binary neural network uses high speed pattern matching to recall a candidate set of matching records, which are then processed by a conventional k-NN appr...

In this paper, statistical, artificial neural networks and fuzzy based feature evaluation indices are analysed in order to determine the importance of prostate cancer prognostic markers. Seven prognostic markers are assessed in terms of 3 output classes using logistic regression as a statistical method, multilayer feedforward back propagation neural networks (MLFFBPNN) as a neural network tool,...

The most commonly used objective function in Artificial Neural Networks (ANNs) is the sum of squared errors. This requires the target and forecasted output vector to have the same dimension. In the context of nonlinear financial time series, both conditional mean and variance (volatility) tend to evolve over time. It is therefore of interest to consider neural networks with two-dimensional outp...