Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

BP: Fachverband Biologische Physik

BP 14: Posters: Neurophysics

BP 14.5: Poster

Montag, 16. März 2015, 17:30–19:30, Poster A

An objective function for Hebbian self-stabilizing neural plasticity rules — •Rodrigo Echeveste and Claudius Gros — Institute for Theoretical Physiscs, Goethe University Frankfurt, Germany

Objective functions provide a useful framework for the formulation of guiding principles in dynamical systems. In the case of information processing systems, such as neural networks, these guiding principles can be formulated in terms of information theoretical measures with respect to the input and output probability distributions. In the present work, a guiding principle for neural plasticity is formulated in terms of an objective function defined as the Fisher information with respect to an operator that we denote as the synaptic flux[1]. By minimization of this objective function, we obtain synaptic plasticity rules that both account for Hebbian/anti-Hebbian learning and are self-limiting to avoid unbounded weight growth.

As an application, the non-linear bars problem[2] is studied, in which each neuron is presented with a grid of inputs, depicting the superposition of a random set of bars. We show that, under the here presented rules, the neurons are able to learn single bars or points (the independent components of the input), even when these are never presented in isolation.

[1] Echeveste, R., & Gros, C. (2014). Generating functionals for computational intelligence: The Fisher information as an objective function for self-limiting Hebbian learning rules. Front. Robot. AI, 1, 1.

[2] Földiak, P. (1990). Forming sparse representations by local anti-Hebbian learning. Biological cybernetics, 64(2), 165-170.