Hebb's rule is assumed to be closely associated with biological learning. I
t has not been so far a source of powerful learning algorithms for artifici
al neural networks. We point to the fact that Hebb's rule implemented in a
quantum algorithm leads to learning algorithm converging much faster. The o
rigin of the difference is "quantum entanglement". Quantum entanglement may
have a neuronal equivalent, which may be the reason why biological learnin
g uses rules which are difficult to implement on a computer. (C) 2000 Elsev
ier Science B.V. All rights reserved.