Motivated by the application of seismic inversion in the petroleum industry we consider a hidden Markov model with two hidden layers. The bottom layer is a Markov chain and given this the variables in the second hidden layer are assumed conditionally independent and Gaussian distributed. The observation process is assumed Gaussian with mean values that are linear functions of the second hidden ...

Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. But due to the greedy scheme of the layerwise training technique, the parameter...

In this paper, we present a novel Deep Triphone Embedding (DTE) representation derived from Deep Neural Network (DNN) to encapsulate the discriminative information present in the adjoining speech frames. DTEs are generated using a four hidden layer DNN with 3000 nodes in each hidden layer at the first-stage. This DNN is trained with the tied-triphone classification accuracy as an optimization c...

The modeling process is to find a parametric model whose dynamic behavior close to that process. This model will be used to make predictions of the process output, or to simulate the process in a control system...etc. In this work we used RBF neural networks for modeling nonlinear systems. Generally the problem in neural networks is often to find a better structure. We propose in this work a me...

Nowadays, one of the main issues to create challenges in medicine sciences by developing technology is the disease diagnosis with high accuracy. In the recent decades, Artificial Neural Networks (ANNs) are considered as the best solutions to achieve this goal and involve in widespread researches to diagnose the diseases. In this paper, we consider a Multi-layer Perceptron (MLP) ANN using back p...

In this paper, we investigate the decision making ability of a fully complex-valued radial basis function (FC-RBF) network in solving real-valued classification problems. The FC-RBF classifier is a single hidden layer fully complex-valued neural network with a nonlinear input layer, a nonlinear hidden layer, and a linear output layer. The neurons in the input layer of the classifier employ the ...

The problem of short-term electric load forecasting (STLF) is considered. A modified architecture of Elman-type recurrent neural network is proposed. It utilizes a special fuzzification layer to deal with quantitative as well as ordinal and nominal data. The second hidden layer of the network consists of standard Rosenblatt-type neurons with sigmoidal activation functions. The context layer is ...

The task of part-of-speech (POS) language modeling typically includes a very small vocabulary, which significantly differs from traditional lexicalized language modeling tasks. In this project, we propose a high-order n-gram model and a stateof-the-art recurrent neural network model, which aims at minimizing the variance in this POS language modeling task. In our experiments, we show that the r...

A new RNN-based prosodic information synthesizer for Mandarin Chinese text-to-speech (TTS) is proposed in this paper. Its four-layer recurrent neural network (RNN) generates prosodic information such as syllable pitch contours, syllable energy levels, syllable initial and final durations, as well as intersyllable pause durations. The input layer and first hidden layer operate with a word-synchr...

Simple recurrent networks were trained with sequences of phonemes from a corpus of Turkish words. The network's task was to predict the next phoneme. The aim of the study was to look at the representations developed within the hidden layer of the network in order to investigate the extent to which such networks can learn phonological regularities from such input. It was found that in the differ...