Artificial neural network: Difference between revisions
imported>Felipe Ortega Gutiérrez No edit summary |
imported>Subpagination Bot m (Add {{subpages}} and remove any categories (details)) |
||
| Line 1: | Line 1: | ||
{{subpages}} | |||
'''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 neuron|artificial neurons]], in which the processing behavior is stored in the node interconnections as values called ''weights'', which represent the strength of each neural connection, obtained after processing a sequence of patterns. | '''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 neuron|artificial neurons]], in which the processing behavior is stored in the node interconnections as values called ''weights'', which represent the strength of each neural connection, obtained after processing a sequence of patterns. | ||
| Line 7: | Line 9: | ||
* [[Artificial neuron]] | * [[Artificial neuron]] | ||
* [[Connectionism]] | * [[Connectionism]] | ||
Revision as of 20:19, 24 September 2007
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, in which the processing behavior is stored in the node interconnections as values called weights, which represent the strength of each neural connection, obtained after processing a sequence of patterns.
Adaptation and Learning
When a neuron receives and processes an input signal, it changes the weight value assigned to the input received. The weighted signals are summed to form the activation value, which is filtered by a function called transfer function. Changes in a specific neuron's behavior produces changes in the entire neural network, and this is basically how the neural networks learn.