Robustness of Hebbian and anti-Hebbian Learning
Péter Aszalós, Szabolcs Kéri, Gyula Kováács, György Benedek, Zoltán Janka, and András Lõrincz
IJCNN, Wahington
1999
Abstract
This paper presents a generative data reconstruction neural network model
equipped with plastic lateral connections. The model is capable of capturing
basic phenomena related to category formation. It explains category formation
as an effect of cumulative memory traces at the level of lateral connectivity.
The formed memory traces change network activity that is the basis of
categorization according to the model. This change however depends on the structure
of the lateral connectivity and on the stimuli used in demonstrations. We argue
that the model resolves the seemingly contradictory demonstrational results
carried out with Alzheimer disease (AD) patients on category formation. We
consider different stimulus sets and degraded lateral connectivity and show that
the categorization probability can change from monotone to non-monotone functions
depending on the sets.
