Using statistical mechanics results, I calculate learning curves (average generalization error) for Gaussian processes (GPs) and Bayesian neural networks (NNs) used for regression. Applying the results to learning a teacher defined by a two-layer network, I can directly compare GP and Bayesian NN learning. I find that a GP in general requiresO(ds)-training examples to learn input features of or...

Selection of neural network learning rates to obtain satisfactory performance from neural network controllers is a challenging problem. To assist in the selection of learning rates, this paper investigates robotic system sensitivity to neural network (NN) learning rate. The work reported here consists of experimental and simulation results. A neural network controller module, developed for the ...

In this paper we present a hybrid recognition system that integrates hidden Markov models (HMM) with neural networks (NN) in a probabilistic framework. The input data is processed first by a lexicon–driven word recognizer based on HMMs to generate a list of the candidateN–best– scoring word hypotheses as well as the segmentation of such word hypotheses into characters. An NN classifier is used ...

This paper presents a new feature selection (FS) algorithm based on the wrapper approach using neural networks (NNs). The vital aspect of this algorithm is the automatic determination of NN architectures during the FS process. Our algorithm uses a constructive approach involving correlation information in selecting features and determining NN architectures. We call this algorithm as constructiv...

This paper investigates the combination of different acoustic features. Several methods to combine these features such as concatenation or LDA are well known. Even though LDA improves the system, feature combination by LDA has been shown to be suboptimal. We introduce a new method based on neural networks. The posterior estimates derived from the NN lead to a significant improvement and achieve...

In this paper we propose a Multilayer Perceptron Neural Network (MLP NN) consisting of fuzzy flip-flop neurons based on various fuzzy operations applied in order to approximate a real-life application, two input trigonometric functions, and two and six dimensional benchmark problems. The Bacterial Memetic Algorithm with Modified Operator Execution Order algorithm (BMAM) is proposed for Fuzzy Ne...

Duration modeling is a fundamental task of prosody generation for Text To Speech (TTS) systems. The objective of this task is to predict the duration of a speech unit from its phonological representation. Duration modeling has a significant influence on the intelligibility and the naturalness of the synthesized speech. This paper presents a Neural Network (NN) based approach to predict the dura...

In this work we look for a general neural network model that resembles the interactions between glucose concentration levels and amount of insulin injected in the bodies of diabetics. We use real data for 70 different patients of diabetics and build on it our model. Two types of neural networks (NN’s) are experimented in building that model; the first type is called the Levenberg-Marquardt (LM)...

A Neural Network (NN) approach is studied in deriving information of bathymetry for optically shallow waters. In this study, more than 7000 remote-sensing reflectance (ratio of waterleaving radiance to downwelling irradiance above the surface) spectra for shallow waters were created with a semi-analytical model. This synthetic data base covered chlorophyll-a concentrations from 0.2 to 6 mg/m^3,...

This paper describes a neural network architecture for emotion recognition for human-computer interfaces and applied systems. In the current research, we propose a combination of the most recent biometric techniques with the neural networks (NN) approach for real-time emotion and behavioral analysis. The system will be tested in real-time applications of customers’ behavior for distributed on-l...