A neural network is an interconnected group of biological neurons. In modern usage the term can also refer to artificial neural networks, which are constituted of artificial neurons. Thus the term 'Neural Network' specifies two distinct concepts:
Please see the corresponding articles for details on artificial neural networks or biological neural networks. This article focuses on the relationship between the two concepts.
Neural networks are made of units that are often assumed to be simple in the sense that their state can be described by single numbers, their "activation" values. Each unit generates an output signal based on its activation. Units are connected to each other very specifically, each connection having an individual "weight" (again described by a single number). Each unit sends its output value to all other units to which they have an outgoing connection. Through these connections, the output of one unit can influence the activations of other units. The unit receiving the connections calculates its activation by taking a weighted sum of the input signals (i.e. it multiplies each input signal with the weight that corresponds to that connection and adds these products). The output is determined by the activation function based on this activation (e.g. the unit generates output or "fires" if the activation is above a threshold value). Networks learn by changing the weights of the connections.
More on [ Neural network ]
Belief Networks
Machine Learning :: Artificial Intelligence
Vision :: Artificial Intelligence
Artificial Life
Neurology
Neurobiology :: Biology
Bayesian Analysis :: Statistics
Cognitive Science :: Social Sciences
Neuropsychology :: Psychology
Signal Processing :: Electronics

Neural Network FAQ - This FAQ from comp.ai.neural-nets contains the most commonly asked questions about neural networks, including some great introductory material.
Bibliographies on Neural Networks - Part of the collection of computer science bibliographies.
Meta Description: [ Bibliographies on Neural Networks, part of the Collection of Computer Science Bibliographies ]
500
Boosting Research Site - Scientific homepage on boosting and ensemble learning methods.
Meta Description: [ Scientific Homepage on Boosting and Ensemble Learning Methods: Combining Neural Networks, Decision Trees or other weak learners to improve the generalization performance ]
David E. Rumelhart Prize - An annual award for contributions to the formal analysis of human cognition.
Evolutionary Design of Neural Architectures - A repository maintained by the Artificial Intelligence Research Group led by Vasant Honavar in the Department of Computer Science at Iowa State University.
Gaussian Processes - A website keeping track of developments in Gaussian processes. Has links to online papers and their authors and software.
Maximum Entropy Online Resources - Workshops, tutorials, papers and software related to maximum entropy.
Neural Network Applications - Applications of neural networks for feature selection, dimension reduction and data mining.
Neural Network Centers Around the World - Collection of Neural Network resources sorted by topic.
Meta Description: [ Neural Network Resources page contains extensive information and numerous links to Software, Journals, Books, Societies, Databases, Newsgroups, Archives, E-Lists, etc. Resources are well organized, thoroughly catalogued and presented in easy-to-access manner with user friendly graphical interface. ]
Neuroinformatics - A hub for the neuroinformatics community, with information on workshops and courses. Also hosts the comp-neuro mailing list.
Meta Description: [ The Neuroinformatics site. ]
Principal Curves Page - Introduction to principal curves, with summary of and links to publications, demo, and software.
Meta Description: [ principal curves ]
Reinforcement Learning Repository - A centralized resource for researchers of reinforcement learning. Maintained at University of Massachusetts, Amherst.
Sequential Monte Carlo Methods - Website dedicated to sequential data analysis and tracking using particle filters.
Meta Description: [ Sequential Monte Carlo Methods (Particle Filtering) Homepage ]
| MouseGestures - Neural Network Project ETSII ULL 01 |