AUTHOR=Echeveste Rodrigo , Gros Claudius
TITLE=Generating Functionals for Computational Intelligence: The Fisher Information as an Objective Function for Self-Limiting Hebbian Learning Rules
JOURNAL=Frontiers in Robotics and AI
VOLUME=Volume 1 - 2014
YEAR=2014
URL=https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2014.00001
DOI=10.3389/frobt.2014.00001
ISSN=2296-9144
ABSTRACT=
Generating functionals may guide the evolution of
a dynamical system and constitute a possible route
for handling the complexity of neural networks as
relevant for computational intelligence. We propose and
explore a new objective function which allows to
obtain plasticity rules for the afferent synaptic
weights. The adaption rules are Hebbian and self-limiting
and result from the minimization of the the Fisher
information with respect to the synaptic flux.
We perform a series of simulations examining the behavior of
the new learning rules in various circumstances. The vector
of synaptic weights aligns with the principal direction of
input activities, whenever one is present. A linear
discrimination is performed when there are two or more principal
directions; directions having bimodal firing-rate
distributions, being characterized by a negative excess
kurtosis, are preferred.
We find robust performance and full homeostatic
adaption of the synaptic weights results as a by-product
of the synaptic flux minimization. This self-limiting behavior
allows for stable online learning for arbitrary durations.
The neuron acquires new information when the statistics of
input activities is changed at a certain point of the simulation,
showing however a distinct resilience to unlearn previously
acquired knowledge. Learning is fast when starting with randomly
drawn synaptic weights and substantially slower when the
synaptic weights are already fully adapted.