The main objective of this paper is to introduce a new intelligent optimization technique that uses a predictioncorrectionstrategy supported by a recurrent neural network for finding a near optimal solution of a givenobjective function. Recently there have been attempts for using artificial neural networks (ANNs) in optimizationproblems and some types of ANNs such as Hopfield network and Boltzm...

Data generated from real world events are usually temporal and contain multimodal information such as audio, visual, depth, sensor etc. which are required to be intelligently combined for classification tasks. In this paper, we propose a novel generalized deep neural network architecture where temporal streams from multiple modalities are combined. There are total M+1 (M is the number of modali...

We describe the use of stochastic Petri nets (SPNs) and stochastic reward nets (SRNs) which are SPNs augmented with the ability to specify output measures as reward-based functions, for the evaluation of reliability for complex systems. The solution of SRNs involves generation and analysis of the corresponding Markov reward model. The use of SRNs in modeling complex systems is illustrated throu...

Analytical modeling is a crucial part in the analysis and design of computer systems. Stochastic Petri Nets represent a powerful tool, widely used for dependability, performance and performability modeling. Many structural and stochastic extensions have been proposed so as to increase their modeling power. In this paper we review the main structural and stochastic extensions of Petri nets, by p...

A recurrent neural network is studied in this paper. A multi–context–recurrent neural network is defined and trained with back propagation, and is then applied to the short–term energy load forecasting task. The idea is to predict a daily maximum load for an arbitrary month ahead. A multi–context–recurrent neural network model was simulated and trained with different training sets to predict th...

An important goal of an automatic classifier is to learn the best possible generalization from given training material. One possible improvement over a standard learning algorithm is to train several related tasks in parallel. We apply the multi-task learning scheme to a recurrent neural network estimating phoneme posterior probabilities and HMM state posterior probabilities, respectively. A co...

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asy...

The formation of protein secondary structure especially the regions of β-sheets involves long-range interactions between amino acids. We propose a novel recurrent neural network architecture called Segmented-Memory Recurrent Neural Network (SMRNN) and present experimental results showing that SMRNN outperforms conventional recurrent neural networks on long-term dependency problems. In order to ...