Artificial neural network: Difference between revisions
imported>Felipe Ortega Gutiérrez No edit summary |
imported>Felipe Ortega Gutiérrez |
||
| Line 6: | Line 6: | ||
==Adaptation and Learning== | ==Adaptation and Learning== | ||
Learning in neural networks can be supervised or not unsupervised, and it's often produced by a learning algorithm. Learning is subject to different conditions like the way neurons are associated and the properties of every network component, such as neurons and axons, and for this reason, it's not guaranteed. | |||
==See also== | ==See also== | ||
* [[Artificial neuron]] | * [[Artificial neuron]] | ||
* [[Connectionism]] | * [[Connectionism]] | ||
Revision as of 23:31, 8 April 2008
Artificial Neural Networks (ANNs for short) are a connectionist processing model inspired on the biological neural networks. Artificial neural networks are composed by simple nodes called artificial neurons. They can be implemented via hardware (i.e: electronic devices) of software (i.e: computer simulations).
In some models, the network behavior is stored in the connections between processing units in values called weights, which represent the strength of each link, equivalent to many components of its biological counterpart.
Adaptation and Learning
Learning in neural networks can be supervised or not unsupervised, and it's often produced by a learning algorithm. Learning is subject to different conditions like the way neurons are associated and the properties of every network component, such as neurons and axons, and for this reason, it's not guaranteed.