RT Journal Article
SR Electronic
T1 Efficiency of local learning rules in threshold-linear associative networks
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.07.28.225318
DO 10.1101/2020.07.28.225318
A1 Francesca Schönsberg
A1 Yasser Roudi
A1 Alessandro Treves
YR 2020
UL http://biorxiv.org/content/early/2020/07/29/2020.07.28.225318.abstract
AB We show that associative networks of threshold linear units endowed with Hebbian learning can operate closer to the Gardner optimal storage capacity than their binary counterparts and even surpass this bound. This is largely achieved through a sparsification of the retrieved patterns, which we analyze for theoretical and empirical distributions of activity. As reaching the optimal capacity via non-local learning rules like back-propagation requires slow and neurally implausible training procedures, our results indicate that one-shot self-organized Hebbian learning can be just as efficient.Competing Interest StatementThe authors have declared no competing interest.