Independent, again

[Terry Sejnowski]

There are two types of LTP in the hippocampus, one in area CA1
(and elsewhere) that depends on the NMDA receptor (and is blocked by
AP5) and another type in area CA3 that is not blocked by AP5.
The latter appears not be associative and may not be Hebbian
(but the experimental evidence is not yet definitive on this point).

In addition to heterosynaptic depression (postsynaptic activity
in the absence of presynaptic activity) there is also evidence
for homosynaptic depression (presynaptic activity in the absence of
postsynaptic activity).  For a review of these mechanisms, see
Sejnowski et al., Induction of synaptic plasticity by Hebbian
covariance in the hippocampus, In:  R. Durbin, C. Miall and G. Mitchison.
(Eds.), The Computing Neuron, Addison-Wesley, 1989.  Incidently,
this collection of papers is one of the best on the interface of
biology with computational models.  Another good recent collection
specifically on biologically relevant connectionist models is
Connectionist Modeling and Brain Function, Hanson and Olson (Eds.),
MIT Press, 1990.

The emerging evidence from neurobiologists is that there is a
multiplicity of mechanisms for plasticity at synapses.  Furthermore,
there are mechanisms that can change the excitability of a neuron,
such as changing the density or voltage dependence of ion-selective
channels in the membrane.  This is similar to changing the threshold
and shape of the nonlinearity, except that the change may be specific
to a dendritic branch, not the whole neuron.  This gives Nature
(and modelers) a much richer palate of mechanisms to work with.

Terry

-----