Oja's learning rule, or simply Oja's rule, named after a Finnish computer scientist Erkki Oja, is a model of how neurons in the brain or in artificial neural networks change connection strength, or learn, over time. It is a modification of the standard Hebb's Rule (see Hebbian learning) that, through multiplicative normalization, solves all stability problems and generates an algorithm for principal components analysis. This is a computational form of an effect which is believed to happen in biological neurons.
Read more about Oja's Rule: Theory, Applications, See Also
Famous quotes containing the word rule:
“Good taste is either that which agrees with my taste or that which subjects itself to the rule of reason. From this we can see how useful it is to employ reason in seeking out the laws of taste.”
—G.C. (Georg Christoph)