
	Where results make sense

Topic: Neural networks

Related Topics

Artificial neural network

Neural nets

Neuroevolution

Connectionism

Intelligent control

Pattern recognition

Supervised learning

Computational learning theory

State space (controls)

Machine learning

Logistic regression

C syntax

In the News (Tue 15 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	OVERVIEW OF NEURAL NETWORKS
		Nonetheless, network behavior is important, especially in light of evidence for so-called "emergent properties", ie, properties of networks that are not obvious from an understanding of neuron physiology.
		Although neural networks as they are implemented on computers were inspired by the function of biological neurons, many of the designs have become far removed from biological reality.
		Computer neural network models are described in terms of their architecture (patterns of connection) and in terms of the way they are trained (rules for modifying weights).
	www.benbest.com /computer/nn.html (2933 words)

	Neural Networks
		Autoassociative networks are feedforward networks whose inputs and outputs are identical with network training aimed at approximating the consequent identity mapping between network input and output.
		The network consists of an input layer followed by a non-linear hidden layer (the bottleneck layer), a second non-linear hidden layer and finally the output layer of the same dimension as the input.
		The industrial application of neural network modelling in the general area of process engineering have demonstrated their significant potential in process modelling and control with applications in polymersisation, bioprocessing and the modelling of chemical engineering unit processes.
	www.ncl.ac.uk /cpact/neural_networks_nf.html (2338 words)

	Neural Networks Introduction
		Neural networks have been shown to be particularly useful in solving problems where traditional artificial intelligence techniques involving symbolic methods have failed or proved inefficient.
		A three-layer backpropagation neural network was developed to predict the frequency of serious ADR cases for 17 particular NOSAIDs, using four inputs, each representing a particular property of the drugs.
		Such a neural network might be used to predict the ADR rate for new drugs, as well as to determine the properties that tend to make for "safe" drugs.
	uhavax.hartford.edu /compsci/neural-networks-tutorial.html (3432 words)

	Neural networks : Encyclopedia
		These neural networks are very much inspiret of the way they imagine our own brain works.
		We still seek to make artificial neural networks able to solve these problems, but in order to do that, we must first know how it is we do it ourselves.
		Recurrent neural networks is a network having one or more neurons that feeds data back into the network, so that they can alter their own input.
	library.thinkquest.org /C007009/idb/encyclopedia.html (1437 words)

	Neural Networks Software: Train, Visualize, and Validate Neural Network Models
		Neural Networks also includes special functions to address typical problems in data analysis, such as function approximation, classification and detection, clustering, nonlinear time series, and nonlinear system identification problems.
		Neural Networks is equally suited for advanced and inexperienced users.
		Neural Networks 1.0.2 requires Mathematica 5.0.1-5.2 and is available for all Mathematica platforms.
	www.wolfram.com /products/applications/neuralnetworks (345 words)

	Using Neural Networks
		A probabilistic neural network (PNN) is another neural network variant that is similar to a BP and has the same general architecture as a BP with a similar information flow.
		Neural networks cannot do anything that cannot be done using traditional computing techniques, but they can do some things that would otherwise be very difficult.
		Neural networks are particularly useful with sensor data; data from a complex chemical, manufacturing, or commercial process; and analog problems.
	pubs.acs.org /hotartcl/tcaw/99/nov/simon.html (2112 words)

	INNS.org - Neural Networks Journal
		Neural Networks is the archival journal of the world's oldest neural modeling society: the International Neural Network Society.
		Neural Networks is unique in its range and provides a forum for developing and nurturing an international community of scholars and practitioners who are interested in all aspects of neural networks and related approaches to computational intelligence.
		Neural Networks welcomes high quality articles that contribute to the full range of neural networks research, ranging from behavioral and brain modeling, through mathematical and computational analyses, to engineering and technological applications of systems that significantly use neural network concepts and algorithms.
	www.inns.org /nnjournal.asp (385 words)

	Neural Networks
		Neural networks have seen an explosion of interest over the last few years, and are being successfully applied across an extraordinary range of problem domains, in areas as diverse as finance, medicine, engineering, geology and physics.
		This is the type of network discussed briefly in previous sections: the units each perform a biased weighted sum of their inputs and pass this activation level through a transfer function to produce their output, and the units are arranged in a layered feedforward topology.
		Neural network error surfaces are much more complex, and are characterized by a number of unhelpful features, such as local minima (which are lower than the surrounding terrain, but above the global minimum), flat-spots and plateaus, saddle-points, and long narrow ravines.
	www.statsoft.com /textbook/stneunet.html (17723 words)

	Neural Networks
		Neural networks have seen an explosion of interest over the last few years, and are being successfully applied across an extraordinary range of problem domains, in areas as diverse as finance, medicine, engineering, geology and physics.
		This is the type of network discussed briefly in previous sections: the units each perform a biased weighted sum of their inputs and pass this activation level through a transfer function to produce their output, and the units are arranged in a layered feedforward topology.
		Neural network error surfaces are much more complex, and are characterized by a number of unhelpful features, such as local minima (which are lower than the surrounding terrain, but above the global minimum), flat-spots and plateaus, saddle-points, and long narrow ravines.
	www.statsoftinc.com /textbook/stneunet.html (17723 words)

	Introduction to Backpropagation Neural Networks (Site not responding. Last check: 2007-10-09)
		Neural networks are modelled after the brain (not necessarily a human brain) and provide the learning algorythm that does not require any knowkedges of the formulas for the process being researched, instead, it is based on the familiarity and pattern recognition.
		The importance of neural networks in data mining is in their ability to find non-evident dependencies, thereby reducing dimension and increasing the quality of an answer.
		Neural networks do implement some kind of the fuzzy logic, though it is not the fuzzy logic as it is formally defined.
	cortex.snowseed.com /neural_networks.htm (5135 words)

	Neural Networks
		Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques.
		The commonest type of artificial neural network consists of three groups, or layers, of units: a layer of "input" units is connected to a layer of "hidden" units, which is connected to a layer of "output" units.
		Neural networks were used to discover the influence of undefined interactions by the various variables.
	www.doc.ic.ac.uk /~nd/surprise_96/journal/vol4/cs11/report.html (6614 words)

	Neural Networks & Connectionist Systems
		Neural models of intelligence emphasize the brain's ability to adapt to the world in which it is situated by modifying the relationships between individual neurons.
		Neural networks are usually characterized in terms of the number and types of connections between individual processing elements, called neurons, and the learning rules used when data is presented to the network.
		Neural networks, unlike fuzzy logic, seek to reproduce the versatility of the human brain in recognizing the end-to-end, input-to-output behavior of a system without understanding all the processes taking place within it.
	www.aaai.org /aitopics/html/neural.html (4359 words)

	generation5 - An Introduction to Neural Networks
		This area of neural networking is the "fuzziest" in terms of a definite set of rules to abide by.
		Neural networks are designed to work with patterns - they can be classified as pattern classifiers or pattern associators.
		Other problems with neural networks are the lack of defining rules to help construct a network given a problem - there are many factors to take into consideration: the learning algorithm, architecture, number of neurons per layer, number of layers, data representation and much more.
	www.generation5.org /content/2000/nnintro.asp (1242 words)

	Train To Gain With Neural Networks
		Neural networks are state-of-the-art, trainable algorithms that emulate certain major aspects in the functioning of the human brain.
		Neural networks can be applied gainfully by all kinds of traders, so if you're a trader and you haven't yet been introduced to neural networks, we'll take you through this method of technical analysis and show you how to apply it to your trading style.
		As far as trading is concerned, neural networks are a new, unique method of technical analysis, intended for those who take a thinking approach to their business and are willing to contribute some time and effort to make this method work for them.
	www.investopedia.com /articles/trading/06/neuralnetworks.asp (1584 words)

	Neural Networks Software: STATISTICA Automated Neural Networks Software by StatSoft
		The popularity of neural network methodology is rapidly growing in a wide variety of areas from basic research to data mining applications, business forecasting and risk management, engineering, and others (see Example Applications).
		Trained neural networks can be applied to new data (for prediction) in several ways: you can save the trained neural networks, and later retrieve them to be applied to new data (for prediction, predicted classification, or forecasting).
		Neural networks are noise tolerant and allow for robust pattern recognition of particle physics data with large statistical noise.
	www.statsoft.com /products/stat_nn.html (2168 words)

	Neural Networks at your Fingertips
		The network is then used to solve a well-known optimization problem: The weight matrix is chosen such that the global minimum of the energy function corresponds to a solution of a particular instance of the traveling salesman problem.
		The counterpropagation network is a competitive network, designed to function as a self-programming lookup table with the additional ability to interpolate between entries.
		The task of the network is to establish a mapping between the state variables of the pole and the optimal force to keep it balanced.
	www.neural-networks-at-your-fingertips.com (1029 words)

	Connectionism (Stanford Encyclopedia of Philosophy)
		Neural networks are simplified models of the brain composed of large numbers of units (the analogs of neurons) together with weights that measure the strength of connections between the units.
		Neural networks are also particularly well adapted for problems that require the resolution of many conflicting constraints in parallel.
		This suggests that neural network models serve as counterexamples to the idea that the language of thought is a prerequisite for human cognition.
	plato.stanford.edu /entries/connectionism (7688 words)

	Neural Networks - NeuroSolutions, Neural Network Software
		Neural networks are an exciting form of artificial intelligence which mimic the learning process of the human brain in order to extract patterns from historical data.
		This leading edge neural network development software combines a modular, icon-based network design interface with an implementation of advanced learning procedures, such as conjugate gradients and backpropagation through time.
		The toolbox features 15 neural models, 5 learning algorithms and a host of useful utilities integrated in an easy-to-use interface, which requires “next to no knowledge” of neural networks to begin using the product.
	www.neurosolutions.com (569 words)

	NeuroDimension - Neural Network Software, Neural Net Software, Neural Networks, Neural Nets
		Neural networks and genetic algorithms are exciting technologies in the field of artificial intelligence.
		Our neural network software products are among the most powerful and flexible on the market today, yet their intuitive graphical user interfaces make them incredibly easy to use.
		This advanced technical analysis trading software combines neural network and genetic algorithm technologies with traditional technical analysis to create a highly effective tool for financial modeling.
	www.nd.com (474 words)

	Mathtools.net : Excel/Neural Networks
		Neural network technology and genetic algorithms are advanced technologies in the field of artificial intelligence.
		Neuralyst is a general purpose neural network engine that has been integrated with Microsoft® Excel on Windows or Macintosh systems.
		Neural networks can perform pattern matching or feature recognition, particularly on "noisy" or "fuzzy" data.
	www.mathtools.net /Excel/Neural_Networks/index.html (867 words)

	An Introduction to Neural Networks
		neural networks are based on the parallel architecture of animal brains.
		Neural networks cannot do anything that cannot be done using traditional computing techniques, BUT they can do some things which would otherwise be very difficult.
		This is one of the first large-scale applications of neural networks in the USA, and is also one of the first to use a neural network chip.
	www.cs.stir.ac.uk /~lss/NNIntro/InvSlides.html (2217 words)

	Neural Network Forecasting ... all you need to know!
		We seek to unite information on neural network forecasting, spread across various disciplines of intelligent time series analysis and time series prediction with neural nets, intelligent demand planning in Operations Management, predictive analytics and temporal data mining using computational intelligence and theoretical research on neural networks in artificial intelligence.
		We attempt to organise these pages by evaluating potential information on neural networks for forecasting and identifying the most relevant, in order to allow efficient and effective structuring of information.
		As these webpages are something of a neural forecasting FAQ, reading list and a summary of the state of thttp://www.neural-forecasting-competition.com/he art, we try to avoid duplicating of information on general neural network issues that is already found in the excellent NN FAQ at SAS Institute by W.S. Sarle
	www.neural-forecasting.com (718 words)

	Bibliographies on Neural Networks
		Bibliography on Invariant Pattern Recognition with Neural Networks
		Bibliography of Fault Tolerance related Neural Network literature
		Bibliography on Principal Component Analysis (PCA) Neural Networks
	liinwww.ira.uka.de /bibliography/Neural/index.html (185 words)

	What is neural network? - A Word Definition From the Webopedia Computer Dictionary
		Neural networks are particularly effective for predicting events when the networks have a large database of prior examples to draw on.
		The field of neural networks was pioneered by Bernard Widrow of Stanford University in the 1950s.
		Neural networks are currently used prominently in voice recognition systems, image recognition systems, industrial robotics, medical imaging, data mining and aerospace applications.
	www.webopedia.com /TERM/n/neural_network.html (499 words)

	Tutorials - Neural Networks Warehouse
		A template is created to allow easy creation of new neural networks, where inserting data for pattern recognition is a matter of pasting.
		The Nervous System is used to describe the functionning of neural networks, from a physiological point of view.
		The hopfield network is analysed, as well as its memory capacity.
	neuralnetworks.ai-depot.com /Tutorials.html (1002 words)

	The MathWorks - Neural Network Toolbox - Design and simulate neural networks
		The Neural Network Toolbox extends MATLAB with tools for designing, implementing, visualizing, and simulating neural networks.
		Neural networks are invaluable for applications where formal analysis would be difficult or impossible, such as pattern recognition and nonlinear system identification and control.
		The Neural Network Toolbox provides comprehensive support for many proven network paradigms, as well as graphical user interfaces (GUIs) that enable you to design and manage your networks.
	www.mathworks.com /products/neuralnet (174 words)

	RECURRENT NEURAL NETWORKS - FEEDBACK NETWORKS - LSTM RECURRENT NETWORK - FEEDBACK NEURAL NETWORK - RECURRENT NETS - ...
		The human brain is a recurrent neural network (RNN): a network of neurons with feedback connections.
		Their problems were first rigorously analyzed on Schmidhuber's RNN long time lag project by his former PhD student Hochreiter (1991).
		Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments.
	www.idsia.ch /~juergen/rnn.html (1934 words)

Try your search on: Qwika (all wikis)