On the use of associative memory in Hopfield networks designed to solve propositional satisfiability problems

Hopfield networks are an attractive choice for solving many types of computational problems because they provide a biologically plausible mechanism. The Self-Optimization (SO) model adds to the Hopfield network by using a biologically founded Hebbian learning rule, in combination with repeated network resets to arbitrary initial states, for optimizing its own behavior towards some desirable goal state encoded in the network. In order to better understand that process, we demonstrate first that the SO model can solve concrete combinatorial problems in SAT form, using two examples of the Liars problem and the map coloring problem. In addition, we show how under some conditions critical information might get lost forever with the learned network producing seemingly optimal solutions that are in fact inappropriate for the problem it was tasked to solve. What appears to be an undesirable side-effect of the SO model, can provide insight into its process for solving intractable problems.

[1]  T. Ikegami,et al.  From autopoiesis to self-optimization: Toward an enactive model of biological regulation , 2023, bioRxiv.

[2]  Richard Watson,et al.  The collective intelligence of evolution and development , 2023, Collective Intelligence.

[3]  T. Froese,et al.  Scaling up the self-optimization model by means of on-the-fly computation of weights , 2022, 2022 IEEE Symposium Series on Computational Intelligence (SSCI).

[4]  Armin Biere,et al.  Better Decision Heuristics in CDCL through Local Search and Target Phases , 2022, J. Artif. Intell. Res..

[5]  Malte R. Henningsen-Schomers,et al.  Biological constraints on neural network models of cognitive function , 2021, Nature Reviews Neuroscience.

[6]  Nils B. Weidmann,et al.  Mapping the International System, 1886-2019: The CShapes 2.0 Dataset , 2020, Journal of Conflict Resolution.

[7]  Joao Marques-Silva,et al.  PySAT: A Python Toolkit for Prototyping with SAT Oracles , 2018, SAT.

[8]  Saratha Sathasivam,et al.  Discrete hopfield neural network in restricted maximum k-satisfiability logic programming , 2018 .

[9]  Richard A. Watson,et al.  Transformations in the scale of behavior and the global optimization of constraints in adaptive networks , 2011, Adapt. Behav..

[10]  Richard A. Watson,et al.  Optimization in "self-modeling" complex adaptive systems , 2011, Complex..

[11]  Toby Walsh,et al.  Handbook of Satisfiability: Volume 185 Frontiers in Artificial Intelligence and Applications , 2009 .

[12]  Wan Ahmad Tajuddin Wan Abdullah,et al.  Logic Learning in Hopfield Networks , 2008, ArXiv.

[13]  Felipe Maia Galvão França,et al.  SATyrus: a SAT-based neuro-symbolic architecture for constraint processing , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[14]  Wan Ahmad Tajuddin Wan Abdullah,et al.  Logic programming on a neural network , 1992, Int. J. Intell. Syst..

[15]  Abbott,et al.  Storage capacity of generalized networks. , 1987, Physical review. A, General physics.

[16]  Baldi,et al.  Number of stable points for spin-glasses and neural networks of higher orders. , 1987, Physical review letters.

[17]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[18]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[19]  Daniel Alastair Power,et al.  Distributed associative learning in ecological community networks , 2019 .

[20]  Salil P. Vadhan,et al.  Computational Complexity , 2005, Encyclopedia of Cryptography and Security.

[21]  Juan Luis Castro Peña,et al.  The logic of neural networks , 1998 .

[22]  Gadi Pinkas,et al.  Symmetric Neural Networks and Propositional Logic Satisfiability , 1991, Neural Computation.

[23]  N. J. Cohen,et al.  Higher-Order Boltzmann Machines , 1986 .

[24]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .