We discuss a number of methods for estimating the standard error of predicted values from a multi-layer perceptron. These methods include the delta method based on the Hessian, bootstrap estimators, and the \sandwich" estimator. The methods are described and compared in a number of examples. We nd that the bootstrap methods perform best, partly because they capture variability due to the choice...

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...

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very ...

This paper describes the dynamic control of a 3 degree of freedom (DOF) finger emulating a human finger for reaching a desired fingertip position in space. The control consists of a neural network (NN) which provides the necessary three torques to the phalanges granting a smooth “natural” speed profile of the fingertip motion. To obtain the results, we face these problems: 1) the elimination of...

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...