Independent, again

[Patrick Thomas]

I wonder who is currently supporting the idea of INDEPENDENT (non hebbian)
rules for synaptic plasticity apart from Finkel & Edelman (1). They formulated
a synaptic plasticity mechanism which is based on a PRESYNAPTIC RULE
(the efficacy of the presynaptic terminal is dependent only on the activity
of the presynaptic neuron, no postsynaptic firing or above-treshold
depolarization is necessary, ALL presynaptic terminals are affected) and on
a POSTSYNAPTIC RULE which is a  heterosynaptic modification rule similiar
to that of Changeux, Alkon  and others.

There is general agreement that Hebbs original notion of postsynaptic FIRING
as a condition of synaptic weight increase is inappropriate. Usually a
postsynaptic DEPOLARIZATION is said to be needed with a further refinement
preventing unbounded weight increase, namely some kind of ANTI-HEBB
condition which decreases synaptic weight in the absence of correlated
conditions of "activity" (cf Stent 1973, Palm and others). Of course
there are numerous other variations of Hebb rules not to be considered here
(cf Brown, 1990, Ann Rev NS).

But, what shall we do with the following two facts:

1) No mechanism is known to detect coincidence of pre/postsynaptic "activity".
   The NMDA-Receptor complex is currently en vogue, but available data
   is inconclusive.

2) There is a growing amount of data related to heteroassociative interactions
   LOCAL on the dendritic tree between neighbouring synapses. So why not
   redefine our models based on this observations ?

All of the heteroassociative effects of synaptic plasticity, of course, rely
on some kind of "postsynaptic activity". But this is not meant in the
hebb-sense as to involve the postsynaptic neuron as a functional whole but
rather in the context of local depolarization affecting neighbouring
membrane channel properties, for example. Alkon therefore simulates with
his "neurons" having distinct patches for incoming signals.

In addition to a postsynaptic/heterosynaptic mechanism there is ample
evidence for homo/multisynaptic facilitation and depression which is
independent of postsynaptic activity.

Edelmans DUAL RULES MODEL sketched earlier could therefore well be an
appropriate starting point for the investigation of new learning laws
to be applied within the context of Artificial Neural Networks (actually,
it needs some refinements).

Could someone provide references to work either crushing the idea of
independent modification rules or supporting it ?

Thanx in advance.

Patrick Thomas
Computer Science, Munich Technical University

(1) "Synaptic Function", Edelman/Gall/Cowan (eds), Wiley, 1987.

PS: Bad timing. I bet everbody is in San Diego.

PSS: The Kelso (1986) and Bonhoeffer (1989) results are admittedly a
     challenge to non-hebbian rules. Hopefully a moderate one.