Title—Asymmetric Hebbian learning on recurrent neural network and there dynamics.

 

Abstract—Seminal observations performed by Skarda and Freeman on the olfactory bulb

of rabbits during cognitive tasks have suggested to locate the basal state of behavior in the

network’s spatio-temporal dynamics. Following these neurophysiological observations,

the authors have investigated the possibility to store external stimuli in spatio-temporal

dynamical attractors of recurrent neural networks. To this aim, an efficient learning algorithm,

based on a time asymmetric Hebbian mechanism, has been proposed.

The underlying idea is to obtain -as much as possible- a natural i.e. unconstrained mapping

between the external stimuli and the spontaneous internal dynamics of the network. The

dynamical regime called ”frustrated chaos” by the authors appears to play a substantial role

in the establishment of this mapping and appears as a consequence of the learning procedure.

Adopting a symbolic coding of the output, new investigations

were performed on the presence and the importance of spurious data. It is shown how

the presence of chaos contributes to stop their proliferation without spamming all the phase

state and thus leaving place for both noise robustness and spot for new attractors.