Abstract
Describing the evolution of cognition as an informational process, we want to compare the complexity and computational power of connectionist models of some cognitive functions to the maximal information transmitted in brain relevant genes during neocortex evolution.
In this paper we implement propositional logic as Boolean functions in neural networks and investigate what types of functions emerge in nets with specified architecture (feedforward vs. fully backcoupled) and random weights. For N=2,3 arguments the relative portions of Boolean functions are given as results of a Monte Carlo simulation.
Preview
Unable to display preview. Download preview PDF.
Literature
M.D.S.Braine: On the Relation between the Natural Logic of Reasoning and Standard Logic, Psychological Review 85(1987)1–21.
P.Carnevali & S.Patarnello: Exhaustive Thermodynamical Analysis of Boolean Learning Networks, Europhysics Letters 4(1987)1199–1204.
S.E.Hampson & D.J.Volper: Disjunctive Models of Boolean Category Learning, Biological Cybernetics 56(1987)121–137.
G.L.Hofacker, B.Borstnik & M.Schöniger: Evolutionary Adaption to a Real and an Artificial World, in: Biological and Artificial Intelligence Systems, E.Clementi & S.Chin (Eds.), ESCOM, Leiden 1988.
W.S.McCulloch & W.Pitts: A Logical Calculus of the Ideas Immanent in Nervous Activity, Bulletin of Mathematical Biophysics 5(1943)115–133.
R.Rojas: Theorie der neuronalen Netze, Springer, Berlin1993.
C.Van den Broeck & R.Kawai: Learning in Feedforward Boolean Networks, Physical Review 42(1990) 6210–6218.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weitze, MD., Hofacker, G.L. (1995). The implementation of propositional logic in random neural networks. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_173
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_173
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive