Beyond Hebb: Exclusive-OR and Biological Learning
Konstantin Klemm, Stefan Bornholdt, Heinz Georg Schuster
Abstract
A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error back-propagation, as well as to increase robustness of learning in the presence of noise.
Create a lesson
Related papers
Amplifying Phenomenal Information: Toward a Fundamental Theory of Consciousness
L. Gabora
Cumulant Dynamics of a Population under Multiplicative Selection, Mutation and Drift
Magnus Rattray, Jonathan L. Shapiro
A microsimulation of traders activity in the stock market: the role of heterogeneity, agents' interactions and trade frictions
Giulia Iori
Number-conserving cellular automaton rules
Nino Boccara, Henryk Fuks
The Importance of Being Discrete - Life Always Wins on the Surface
Nadav M. Shnerb, Yoram Louzoun, Eldad Bettelheim et al.
Fitness versus Longevity in Age-Structured Population Dynamics
W. Hwang, P. L. Krapivsky, S. Redner