neural network research papers-13

Artificial neural network implementation on a fine-grained FPGA
P Lysaght, J Stockwood, J Law ,Field-Programmable Logic , 1994 ,Springer

This paper reports on the implementation of an Artificial Neural Network (ANN) on an Atmel
AT6005 Field Programmable Gate Array (FPGA). The work was carried out as an experiment
in mapping a bit-level, logically intensive application onto the specific logic resources of a 

Neural network-based diesel engine emissions prediction using in-cylinder combustion pressure
ML Traver, RJ Atkinson ,SAE transactions, 1999 ,

ABSTRACT This paper explores the feasibility of using in-cylinder pressure-based variables
to predict gaseous exhaust emissions levels from a Navistar T444 direct injection diesel
engine through the use of neural networks. The networks were trained using in-cylinder 

Mapping soil landscape as spatial continua: the neural network approach
AX Zhu ,Water Resources Research, 2000 ,

Abstract. A neural network approach was developed to populate a soil similarity model that
was designed to represent soil landscape as spatial continua for hydroecological modeling
at watersheds of mesoscale size. The approach employs multilayer feed forward neural

Application of an artificial neural network to predict specific class I MHC binding peptide sequences
D Sauer, AP Brunmark ,Nature , 1998 ,

Computational methods were used to predict the sequences of peptides that bind to the
MHC class I molecule, K”. The rules for predicting binding sequences, which are limited, are
based on preferences for certain amino acids in certain positions of the peptide. It is 

Influence of noise on the function of a “physiological” neural network
Biological cybernetics, 1987 ,Springer

A model neural network with stochastic elements in its millisecond dynamics is investigated.
The network consists of neuronal units which are modelled in close analogy to physiological
neurons. Dynamical variables of the network are the cellular potentials, axonic currents 

Breathing pulses in an excitatory neural network
SE Folias ,SIAM J. Appl. Dyn. Syst, 2004 ,

Abstract. In this paper we show how a local inhomogeneous input can stabilize a stationary-
pulse solution in an excitatory neural network. A subsequent reduction of the input amplitude
can then induce a Hopf instability of the stationary solution resulting in the formation of a 

Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm
Soft Computing-A Fusion of Foundations, , 2007 ,Springer

Abstract A multilayer neural network based on multi-valued neurons (MLMVN) is considered
in the paper. A multi-valued neuron (MVN) is based on the principles of multiple-valued
threshold logic over the field of the complex numbers. The most important properties of 

Neural Network Toolbox
M Beale, H Demuth ,For Use with MATLAB, User’s Guide, The , 1998 ,

The software described in this document is furnished under a license agreement. The
software may be used or copied only under the terms of the license agreement. No part of
this manual may be photocopied or reproduced in any form without prior written consent 

Attractor neural network models of spatial maps in hippocampus
M Tsodyks ,Hippocampus, 1999 ,

ABSTRACT: Hippocampal pyramidal neurons in rats are selectively activated at specific
locations in an environment (O’Keefe and Dostrovsky, Brain Res 1971; 34: 171–175).
Different cells are active in different places, therefore providing a faithful representation of 

Predictive modelling of coniferous forest age using statistical and artificial neural networkapproaches applied to remote sensor data
JR Jensen, F Qiu ,International Journal of Remote Sensing, 1999 ,

Abstract. Age is a powerful variable that can be of signi® cant value when modelling the
health of forest-dominated ecosystem. Traditional investigations have attempted to extract
age information from remotely sensed data by regressing the spectral values within situ 

A generic neural network approach for constraint satisfaction problems
EPK Tsang  Neural network applications, Springer-Verlag, 1992 ,

Abstract The Constraint Satisfaction Problem (CSP) is a mathematical abstraction of the
problems in many AI application domains. In many of such applications timely response by a
CSP solver is so crucial that to achieve it, the user may be willing to sacrifice 

Arti” cial neural network for the identi” cation of unknown air pollution sources
SL Reich, DR Gomez ,Atmospheric environment, 1999 ,

Abstract Arti” cial neural networks (ANN), whose performances to deal with pattern
recognition problems is well known, are proposed to identify air pollution sources. The
problem that is addressed is the apportionment of a small number of sources from a data 

Neural network approximation of a hydrodynamic model in optimizing reservoir operation
Proceedings of the second , 1996 ,

ABSTRACT: An approach of models approximation, applicable in the model-based
optimization of water resources, is described. It was applied to the optimization of a system
of the three reservoirs located in the Apure river basin in Venezuela. Its development plan 

Feedback linearization with neural network augmentation applied to X-33 attitude control
E Johnson, AJ Calise ,Proceedings of the , 2000 ,

Abstract In the application of adaptive flight control, significant issues arise due to vehicle
input characteristics such as actuator position limits, actuator position rate limits, and linear
input dynamics. The concept of modifying a reference model to prevent an adaptation law 

A new neural network approach including first guess for retrieval of atmospheric water vapor, cloud liquid water path, surface temperature, and emissivities over
F Aires, C Prigent, WB Rossow ,Journal of geophysical , 2001 ,

Abstract. The analysis of microwave observations over land to determine atmospheric and
surface parameters is still limited due to the complexity of the inverse problem. Neural
network techniques have already proved successful as the basis of efficient retrieval 

Unsupervised neural network learning procedures for feature extraction and classification
S Becker ,Applied Intelligence, 1996 ,Springer

In this article, we review unsupervised neural network learning procedures which can be
applied to the task of preprocessing raw data to extract useful features for subsequent
classification. The learning algorithms reviewed here are grouped into three sections: 

Neural network adaptations to hardware implementations
P Moerland ,Handbook of neural computation, 1997 ,

Abstract. In order to take advantage of the massive parallelism offered by artificial neural
networks, hardware implementations are essential. However, most standard neural network
models are not very suitable for implementation in hardware and adaptations are needed. 

Implementation of a fast artificial neural network library (fann)
S Nissen , , Department of Computer Science University of , 2003 ,

Abstract This report describes the implementation of a fast artificial neural network library in
ANSI C called fann. The library implements multilayer feedforward networks with support for
both fully connected and sparse connected networks. Fann offers support for execution in