Part of Advances in Neural Information Processing Systems 13 (NIPS 2000)
Gal Chechik, Naftali Tishby
The paradigm of Hebbian learning has recently received a novel in(cid:173) terpretation with the discovery of synaptic plasticity that depends on the relative timing of pre and post synaptic spikes. This paper derives a temporally dependent learning rule from the basic princi(cid:173) ple of mutual information maximization and studies its relation to the experimentally observed plasticity. We find that a supervised spike-dependent learning rule sharing similar structure with the ex(cid:173) perimentally observed plasticity increases mutual information to a stable near optimal level. Moreover, the analysis reveals how the temporal structure of time-dependent learning rules is determined by the temporal filter applied by neurons over their inputs. These results suggest experimental prediction as to the dependency of the learning rule on neuronal biophysical parameters