<artificial intelligence> The most common way to train a
neural network; a kind of unsupervised learning; named
after canadian neuropsychologist, Donald O. Hebb.
The algorithm is based on Hebb's Postulate, which states
that where one cell's firing repeatedly contributes to the
firing of another cell, the magnitude of this contribution
will tend to increase gradually with time. This means that
what may start as little more than a coincidental relationship
between the firing of two nearby neurons becomes strongly
causal.
Despite limitations with Hebbian learning, e.g., the inability
to learn certain patterns, variations such as Signal Hebbian
Learning and Differential Hebbian Learning are still used.
