Natural Evolution of Algorithms with Parameter Sensitive Performance
Natural Evolution of Algorithms with Parameter Sensitive Performance
Keywords
Authors
Date
2014-09-04
Language
en
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Computational-level theories of cognition often postulate functions that are computationally
intractable (e.g., NP-hard or worse). This seems to render such theories computationally and
cognitively implausible. One account of how humans may nevertheless compute intractable
functions is that they exploit parameters of the input of these functions to compute the func-
tions e ciently under conditions where the values of those parameters are small. Previous
work has established the existence of such algorithms for various cognitive functions. How-
ever, whether or not these algorithms can evolve in a cognitively plausible manner remains
an open question. In this thesis, we describe the rst formal investigation of this question
relative to the constraint satisfaction model of coherence. In our investigation, we evolved
neural networks for computing coherence under this model. Our simulation results show
that such evolved networks indeed exploit parameters in the same way as known tractable
algorithms for this model.
Description
Citation
Faculty
Faculteit der Sociale Wetenschappen