This paper proposes a version of the backpropagation algorithm which increases the tolerance of a feedforward neural network against deviations in the weight values. These changes can originate either when the neural network is mapped on a given VLSI circuit where the precision and/or weight matching are low, or by physical defects a!ecting the neural circuits. The modi"ed backpropagation algor...

Human Activity Recognition has witnessed a significant progress in the last decade. Although a great deal of work in this field goes in recognizing normal human activities, few studies focused on identifying motion in sports. Recognizing human movements in different sports has high impact on understanding the different styles of humans in the play and on improving their performance. As deep lea...

In this paper, we propose some improvements for the problem of time series prediction with neural networks where a medium-term prediction horizon is needed. In particular, the ionospheric prediction service of the french Centre National d' Etudes des T el ecommunica-tions needs a six-month ahead prediction of a sunspots related time series which has a strong innuence on wave propagation in iono...

Our group is developing artificial neural networks that may be implemented using hybrid semiconductor/molecular (“CMOL”) circuits. Estimates show that such networks (“CrossNets”) may eventually exceed the mammal brain in areal density, at much higher speed and acceptable power consumption. In this report, we demonstrate that CrossNets based on simple (two-terminal) molecular devices can work we...

This paper describes two systems that were used by the NileTMRG for addressing Arabic Sentiment Analysis as part of SemEval-2017, task 4. NileTMRG participated in three Arabic related subtasks which are: Subtask A (Message Polarity Classification), Subtask B (Topic-Based Message Polarity classification) and Subtask D (Tweet quantification). For subtask A, we made use of our previously developed...

We devise a feed-forward Artiicial Neural Network (ANN) procedure for predicting utility loads and present the resulting predictions for two test problems given by \The Great Energy Predictor Shootout-The First Building Data Analysis and Prediction Competition" 1]. Key ingredients in our approach are a method (test) for determining relevant inputs and the Multilayer Perceptron. These methods ar...

We present a perceptron model with processing units consisting of coupled phase oscillators. The processing units are able to compute the input signals through a high order synapse mechanism. We show how a network of these elements can be used in analogy to the classical multilayer feedforward neural network. The main characteristics of the classical multilayer perceptron model are conserved, a...

This paper deals with recurrent neural networks of multilayer perceptron type which are well-suited for speech recognition, specially for phoneme recognition. The ability of these networks has been investigated by phoneme recognition experiments using a number of Japanese words uttered by a native male speaker in a quiet environment. Results of the experiments show that recognition rates achiev...

Product Driven Systems (PDS) architecture needs emulation systems [13]. Discrete events simulation is then often used to build this emulation tool, but emulation model design is not a trivial task. Also, the goal of this paper is the study of the design of a simulation model by reducing its complexity. According to theory of constraints, we want to build reduced models composed exclusively by b...

This paper describes the implementation of a Multilayer Perceptron Neural Network for handwritten digit recognition. The paper provides the knowledge about previously implemented techniques for same application and also provides their merits and demerits. In this paper Optimal Multilayer Perceptron.Neural network has been designed to reduce complexity of the circuit. Results are also stated to ...