neural network research papers-11

Learning of sequential movements by neural network model with dopamine-like reinforcement signal
RE Suri ,Experimental Brain Research, 1998 ,Springer

Abstract Dopamine neurons appear to code an error in the prediction of reward. They are
activated by unpredicted rewards, are not influenced by predicted rewards, and are
depressed when a predicted reward is omitted. After conditioning, they respond to reward-

Neural network fingerprint classification
CL Wilson, GT Candela ,Journal of Artificial Neural , 1994 ,

Abstract A massively parallel ngerprint classi cation system is described that uses image-
based ridge-valley features, KL transforms, and neural networks to perform pattern level
classi cation. The speed of classi cation is 2.65 seconds per ngerprint on a massively 

Network-based intrusion detection using neural networks
A Bivens, C Palagiri, R Smith , Artificial Neural , 2002 ,

ABSTRACT With the growth of computer networking, electronic commerce, and web
services, security of networking systems has become very important. Many companies now
rely on web services as a major source of revenue. Computer hacking poses significant 

A neural network for tornado prediction based on Doppler radar-derived attributes
C Marzban ,Journal of Applied Meteorology, 1996 ,

Abstract The National Severe Storms Laboratory’s (NSSL) Mesocyclone Detection Algorithm
(MDA) is designed to search for patterns in Doppler velocity radar data which are associated
with rotating updrafts in severe thunderstorms. These storm-scale circulations are typically 

More about the difference between men and women: evidence from linear neural networkand the principal-component approach
B Edelman ,PERCEPTION- , 1995 ,

Abstract. The ability of a statistical/neural network to classify faces by sex by means of a
pixelbased representation has not been fully investigated. Simulations with pixel-based
codes have provided sex-classification results that are less impressive than those 

Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model
Y Koike ,Biological Cybernetics, 1995 ,Springer

In this study, human arm movement was re-constructed from electromyography (EMG)
signals using a forward dynamics model acquired by an artificial neural network within a
modular architecture. Dynamic joint torques at the elbow and shoulder were estimated for 

Performance of a neural network: mapping forests using GIS and remotely sensed data
AK Skidmore, BJ Turner, W Brinkhof , and Remote Sensing, 1997 ,

Abstract Neural networks have been proposed to classify remotely sensed and ancillary CIS
data. In this paper, the backpropagation algorithm is critically evaluated, using as an
example, the mapping of a eucalypt forest on the far south coast of New South Wales, 

Efficient Hopfield pattern recognition on a scale-free neural network
D Stauffer, A Aharony, L da Fontoura Costa ,The European Physical , 2003 ,Springer

Abstract: Neural networks are supposed to recognise blurred images (or patterns) of N
pixels (bits) each. Application of the network to an initial blurred version of one of P pre-
assigned patterns should converge to the correct pattern. In the “standard” Hopfield model

Input selection and partition validation for fuzzy modelling using neural network
DA Linkens ,Fuzzy Sets and Systems, 1999 ,

Abstract A simple and e! ective method for selecting signi” cant input variables and
determining optimal number of fuzzy rules when building a fuzzy model from data is
proposed. In contrast to the existing clustering-based methods, in this approach both input 

Neural network vision for robot driving
D Pomerleau ,Intelligent Unmanned Ground Vehicles, 1997 ,Springer

Autonomous navigation is a difficult problem for traditional vision and robotic techniques,
primarily because of the noise and variability associated with real world scenes.
Autonomous navigation systems based on traditional image processing and pattern 

Multisource classification of complex rural areas by statistical and neural-networkapproaches
L Bruuone, C Conese, F Maselli , Engineering & Remote , 1997 ,

Abstract The automatic generation of land-cover inventories by using remote-sensing data is
a very difficult task when complex rural areas are involved. The main difficulties are related
to the characterization of such spectrally complex and heterogeneous environments and 

Genetic set recombination and its application to neural network topology optimisation
NJ Radcliffe  Neural Computing & Applications, 1993 ,Springer

Forma analysis is applied to the task of optimising the connectivity of a feed-forward neural
network with a single layer of hidden units. This problem is reformulated as a multiset
optimisation problem, and techniques are developed to allow principled genetic search 

Neural network classification and prior class probabilities
I Burns, A Back, A Tsoi  Neural networks: tricks of , 1998 ,Springer

A commonly encountered problem in MLP (multi-layer perceptron) classification problems is
related to the prior probabilities of the individual classes-if the number of training examples
that correspond to each class varies significantly between the classes, then it may be 

Relating the land-cover composition of mixed pixels to artificial neural network classification output
GM Foody ,Photogrammetric Engineering and Remote Sensing, 1996 ,

Abstract ses, the classification procedures generally used to produce a~~ tifi~ i~ l neural
networks are attractive for use in the classi- land-cover map are” hard” techniques which
force allocation fication of land cover from remotely sensed data. In common to One class. 

A personal news service based on a user model neural network
A Jennings ,IEICE Transactions on Information and , 1992 ,

Abstract New methods are needed for accessing very large information services. This paper
proposes the use of a user model neural network to allow better access to a news service.
The network is constructed on the basis of articles read, and articles marked as rejected. It 

Prediction of protein structural classes by neural network
YD Cai ,Biochimie, 2004 ,

The results observed by Muskal and Kim [1] suggested that the structural class of a protein
may basically depend on its amino acid composition. Many efforts [2–14] have been made to
predict the structural class of a protein based on its amino acid composition. For a 

Evolving neural network agents in the NERO video game
Proceedings of the , 2005 ,

Abstract-In most modern video games, character behavior is scripted; no matter how many
times the player exploits a weakness, that weakness is never repaired. Yet if game
characters could learn through interacting with the player, behavior could improve during 

Neurofuzzy system-fuzzy inference using a structured neural network
R Masuoka, N Watanabe , Logic & Neural , 1990 ,

We propose a neurofuzzy system that enables conversion between fuzzy systems and
neural networks while augmenting the advantages of both. Systems fit to express fuzziness
are relatively easy to understad, but not so neural networks. Neural networks can learn, 

A bibliography of neural network business applications research: 1994-1998
BK Wong, VS Lai ,Computers and Operations Research, 2000 ,

Abstract The purpose of this paper is to present a comprehensive bibliography of neural
network application research in business during the period of 1994} 1998. Our extensive
literature searches have identi” ed a total of 302 research articles. A classi” cation of these