The natural energy minimization behavior of a dynamical system can be interpreted as a simple optimization process, finding a locally optimal resolution of problem constraints. In human problem solving, high-dimensional problems are often made much easier by inferring a low-dimensional model of the system in which search is more effective. But this is an approach that seems to require top-down domain knowledge—not one amenable to the spontaneous energy minimization behavior of a natural dynamical system. However, in this article we investigate the ability of distributed dynamical systems to improve their constraint resolution ability over time by self-organization. We use a ‘‘self-modeling’’ Hopfield network with a novel type of associative connection to illustrate how slowly changing relationships between system components can result in a transformation into a new system which is a low-dimensional caricature of the original system. The energy minimization behavior of this new system is significantly more effective at globally resolving the original system constraints. This model uses only very simple, and fully distributed, positive feedback mechanisms that are relevant to other ‘‘active linking’’ and adaptive networks. We discuss how this neural network model helps us to understand transformations and emergent collective behavior in various non-neural adaptive networks such as social, genetic and ecological networks.
Abeles, M. ( 1982). Local cortical circuits: An electrophysiological study . Berlin: Springer.
2.
Ackley, D.H., Hinton, G.E., & Sejnowski, T.J. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9, 147-169.
3.
Angeline, P.J., & Pollack, J.B. ( 1992). The evolutionary induction of subroutines. In Proceedings of the 14th Annual Conference of the Cognitive Science Society (pp. 236-241). Lawrence Erlbaum.
4.
Bourgine, P., & Varela, F.J. ( 1992). Toward a practice of autonomous systems. In F. J. Varela & P. Bourgine (Eds.), Toward a Practice of Autonomous Systems : Proceedings of the First European Conference on Artificial Life (pp. xi-xvii). Cambridge, MA: MIT Press.
5.
Chapman, A.C. ( 2009). Control of large distributed systems using games with pure strategy Nash equilibria. Unpublished doctoral dissertation, University of Southampton, UK.
6.
Chapman, A.C.Rogers, A., Jennings, N.R., & Leslie, D.S. (in press). A unifying framework for iterative approximate best response algorithms for distributed constraint optimisation problems. The Knowledge Engineering Review.
Coolen, A.C.C. ( 1991). On the relation between stability parameters and sizes of domains of attraction in attractor neural networks. Europhysics Letters, 16, 73.
9.
Davies, A.P., Watson, R.A., Mills, R., Buckley, C.L., & Noble, J. (in press). If you can’t be with the one you love, love the one you’re with: How individual habituation of agent interactions improves global utility . Artificial Life.
Fernando, C., Goldstein, R., & Szathmáry, E. (2010). The neuronal replicator hypothesis. Neural Computation, 22(11), 2809-2857.
12.
Fernando, C., & Szathmáry, E. (2010). Natural selection in the brain. In Towards a theory of thinking: Vol. 2 (Chapter 20). Springer/Parmenides book series.
13.
Fontanari, J.F. ( 1990). Generalization in a Hopfield network. Journal de Physique, 51, 2421-2430.
14.
Forrest, S., & Mitchell, M. ( 1993). What makes a problem hard for a genetic algorithm? Some anomalous results and their explanation. Machine Learning , 13, 285-319.
15.
Fuller, R.B. ( 1975). SYNERGETICS: Explorations in the geometry of thinking . New York: Macmillan.
16.
Gardner, E. ( 1988). The space of interactions in neural network models . Journal of Physics A: Mathematical and General, 21, 257.
17.
Goetz, P., & Walters, D. ( 1997). The dynamics of recurrent behavior networks. Adaptive Behavior, 6, 247-283.
18.
Goldberg, D.E. ( 1989). Genetic algorithms in search, optimization, and machine learning. Reading, MA: Addison-Wesley .
19.
Gross, T., & Sayama, H. ( 2009). Adaptive networks. Theory, models and applications. Series: Understanding complex systems. Berlin: Springer-Verlag.
20.
Grossberg, S. ( 1978). A theory of human memory: self-organization and performance of sensory-motor codes, maps, and plans. In Progress in theoretical biology (Vol. 5, pp. 233-374). New York: Academic Press.
21.
Haken, H. ( 1983). Synergetics, an introduction: Nonequilibrium phase transitions and self-organization in physics, chemistry, and biology (3rd Rev. ed.). New York: Springer-Verlag .
22.
Hart, S., & Mas-Colell, A. (2000). A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68, 1127-1150.
23.
Hebb, D.O. ( 1949). The organization of behaviour. New York: Wiley.
24.
Hinton, G.E., & Nowlan, S.J. ( 1987). How learning can guide evolution. Complex Systems, 1, 495-502.
25.
Hinton, G.E., & Sejnowski, T.J. (1983). Analyzing cooperative computation . In Proceedings of the 5th Annual Congress of the Cognitive Science Society, Rochester, NY , May 1983.
26.
Hinton, G.E., & Sejnowski, T.J. (1985). Learning in Boltzmann machines . Cognitiva85. Paris, France.
27.
Holland, J.H. ( 2000). Building blocks, cohort genetic algorithms, and hyperplane-defined functions. Evolutionary Computation, 8, 373.
28.
Hopfield, J.J. ( 1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the USA, 79(8), 2554-2558.
29.
Hopfield, J.J., & Tank, D.W. ( 1985). ’Neural’ computation of decisions in optimization problems. Biological Cybernetics, 52, 141-152.
30.
Hopfield, J.J., & Tank, D.W. ( 1986). Computing with neural circuits: A model. Science, 233, 625-633.
31.
Iclanzan, D., & Dumitrescu, D. (2007). Overcoming hierarchical difficulty by hillclimbing the building block structure. In Proceedings of the Genetic and Evolutionary Computation Conference (pp. 1256-1263).
32.
Izquierdo, E.J., & Fernando, C. ( 2008). The evolution of evolvability in gene transcription networks . Artificial Life XI: Proceedings of the Eleventh International Conference on the Simulation and Synthesis of Living Systems (pp. 265- 273). Cambridge, MA: MIT Press.
33.
Jang, J.-S., Kim, M.W., & Lee, Y. ( 1992). A conceptual interpretation of spurious memories in the Hopfield-type neural network. In Proceedings of the International Joint Conference on Neural Networks (Vol 1, pp. 21-26). Piscataway, NJ: IEEE Press.
34.
Jones, A.G., Arnold, S.J., & Bürger, R. (2007). The mutation matrix and the evolution of evolvability. Evolution, 61, 727-745.
35.
Kirchner, M., & Gerhart, J. ( 1998). Evolvability. Proceedings of the National Academy of Sciences of the USA, 95, 8420-8427.
Koza, J.R. ( 1994). Genetic programming II: Automatic discovery of reusable programs. Cambridge, MA: MIT Press .
38.
Kryzhanovsky, B., & Kryzhanovsky, V. (2008). Binary optimization: On the probability of a local minimum detection in random search. ICAISC2008 (pp. 89-100).
39.
Lenaerts, T., Chu, D., & Watson, R. ( 2005). Dynamical hierarchies. Artificial Life , 11, 403-405.
40.
Leslie, D.S., & Collins, E.J. ( 2006). Generalised weakened fictitious play. Games and Economic Behavior, 56(2), 285-298.
41.
Lewis, M. ( 2009). An investigation into the evolution of relationships between species in an ecosystem. Unpublished master’s thesis, University of Southampton, UK.
42.
Maynard Smith, J., & Szathmary, E. ( 1995). Major transitions in evolution. W. H. Freeman.
43.
McClelland, J.L., Rumelhart, D.E., & PDP Research Group (1986). Parallel distributed processing: Explorations in the microstructure of cognition . Vol. 1: Foundations . Cambridge, MA: MIT Press.
44.
Michie, D. ( 1968). Memo functions and machine learning. Nature, 218, 19-22.
45.
Miller, G.A. ( 1956). The magic number seven, plus or minus two: Some limits on our capacity for processing information. Psychological Review, 63, 81-97.
46.
Mills, R. ( 2010). How micro-evolution can guide macro-evolution: Multi-scale search via evolved modular variation. Unpublished doctoral dissertation , University of Southampton, UK.
47.
Mills, R., & Watson, R.A. ( 2005). Genetic assimilation and canalisation in the Baldwin effect. In Proceedings of 8th European Conference on Artificial Life (ECAL 2005), LNCS (pp. 353-362).
48.
Mills, R., & Watson, R.A. ( 2011a). Symbiosis enables the evolution of rare complexes in structured environments. In Proceedings of European Conference on Artificial Life 2009 (pp. 110-117).
49.
Mills, R., & Watson, R.A. ( 2011b). Multi-scale search, modular variation, and adaptive neighbourhoods. Manuscript submitted for publication.
50.
Newman, M.E.J. ( 2003). The structure and function of complex networks . SIAM Review, 45(2), 167-256.
51.
Newman, M. E. J., Barabasi, A. L. & Watts, D. J. (Eds.) (2006). The structure and dynamics of networks. Princeton, NJ: Princeton University Press .
52.
O’Reilly, R.C., & Munakata, Y. ( 2000). Computational explorations in cognitive neuroscience: Understanding the mind by simulating the brain. Cambridge, MA: MIT Press.
53.
Pacheco, J.M., Traulsen, A., & Nowak, M.A. ( 2006). Coevolution of strategy and structure in complex networks with dynamical linking. Physical Review Letters, 97, 258103.
54.
Paine, R.W., & Tani, J. ( 2005). How hierarchical control self-organizes in artificial adaptive systems. Adaptive Behavior, 13, 211-225.
55.
Parter, M., Kashtan, N., & Alon, U. ( 2008). Facilitated variation: How evolution learns from past environments to generalize to new environments. PLoS Computational Biology, 4(11), e1000206.
56.
Pelikan, M. ( 2002). Bayesian optimization algorithm: from single level to hierarchy. Unpublished doctoral dissertation, Dept. of Computer Science at the University of Illinois at Urbana-Champaign, USA.
57.
Pelikan, M., Goldberg, D.E., & Lobo, F. ( 2002). A survey of optimization by building probabilistic models . Computational Optimization and Applications, 21, 5-20.
58.
Powers, S.T. ( 2010). Social niche construction: evolutionary explanations for cooperative group formation. UK: Unpublished doctoral dissertation, ECS , University of Southampton.
59.
Powers, S.T., Mills, R., Penn, A.S., & Watson, R.A. ( 2009). Social niche construction provides an adaptive explanation for new levels of individuality (Abstract). In Proceedings of Workshop on Levels of Selection and Individuality in Evolution , European Conference on Artificial Life 2009.
60.
Powers, S.T., Penn, A.S., & Watson, R.A. ( 2007). Individual selection for cooperative group formation . In Proceedings of European Conference on Artificial Life 2007 (pp. 585-594).
61.
Powers, S.T., Penn, A.S., & Watson, R.A. ( 2011). The concurrent evolution of cooperation and the population structures that support it. Evolution, 65, 1527-1543.
62.
Riegler, A. ( 2008). Natural or internal selection? The case of canalization in complex evolutionary systems. Artificial Life, 14(3), 345-362.
63.
Rosenbloom, P.S., & Newell, A. ( 1986). The chunking of goal hierarchies: A generalized model of practice. In R. S. Michalski, J. G. Carbonell & T. M. Mitchell (Eds.), Machine learning: an artificial intelligence approach, Volume II. Los Altos, CA: Morgan Kaufmann Publishers, Inc.
64.
Santos, F.C., Pacheco, J.M., & Lenaerts, T. ( 2006). Cooperation prevails when individuals adjust their social ties. PLoS Computational Biology, 2(10), e140, 1284-1291.
65.
Siegal, M.L., & Bergman, A. ( 2002). Waddington’s canalization revisited: Developmental stability and evolution. Proceedings of the National Academy of Sciences of the United States of America, 99, 10528-10532.
66.
Simon, H.A. ( 1969). The sciences of the artificial. Cambridge, MA: MIT Press.
Toussaint, M., & von Seelen, W. (2007). Complex adaptation and system structure. BioSystems, 90, 769-782.
69.
Tsirukis, A.G., Reklaitis, G.V., & Tenorio, M.F. ( 1989). Nonlinear optimization using generalized Hopfield networks . Neural Computation, 1, 511-521.
70.
Tsutsumi, K. ( 2003). Relaxing in a warped space: an effect due to the cooperation of static and dynamical neurons. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 897-901).
71.
Van Segbroeck, S., Santos, F.C., Pacheco, J.M., & Lenaerts, T. ( 2010). Coevolution of cooperation, response to adverse social ties and network structure. Games, 1(3), 317-337.
72.
Wagner, G.P., Booth, G., & Bagheri-Chaichian, H. (1997). A population genetic theory of canalization. Evolution, 51, 329-347.
73.
Watson, R.A. ( 2006). Compositional evolution: The impact of sex, symbiosis, and modularity on the gradualist framework of evolution. Cambridge, MA: MIT Press.
74.
Watson, R.A., Buckley, C.L., & Mills, R. ( 2009). The effect of Hebbian learning on optimisation in Hopfield networks (Tech. Rep.). Southampton, UK: ECS, University of Southampton.
75.
Watson, R.A., Buckley, C.L., & Mills, R. ( 2011). Optimisation in ‘self-modelling’ complex adaptive systems. Complexity, 16, 17-26.
76.
Watson, R.A., Buckley, C.L., Mills, R., & Davies, A.P. ( 2010). Associative memory in gene regulation networks . Proceedings of the Twelfth International Conference on the Synthesis and Simulation of Living Systems (Artificial Life XII), 194-202.
77.
Watson, R.A., & Jansen, T. ( 2007). A building-block royal road where crossover is provably essential. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2007) (pp. 1452-1459).
78.
Watson, R.A., Mills, R., & Buckley, C.L. (in press). Global adaptation in networks of selfish components: emergent associative memory at the system scale. Artificial Life.
79.
Watson, R.A., Palmius, N., Jackson, A., Mills, R., Powers, S.T., Buckley, C.L., & Penn, A.S. ( 2011). The origin of group selection via individual selection . Unpublished manuscript.
80.
Watson, R.A., Palmius, N., Mills, R., Powers, S.T., & Penn, A.S. ( 2011). Can selfish symbioses effect higher-level selection? In G. Kampis, I. Karsai & E. Szathmáry (Eds.), ECAL 2009, Part II, LNCS 5778 (pp. 27-36). Berlin/ Heidelberg: Springer-Verlag.
Wolpert, D.H., & Macready, W.G. (1997). No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation , 1, 67.
86.
Young, H.P. ( 2001). Individual strategy and social structure: an evolutionary theory of institutions. Princeton.
87.
Yu, T.-L., Goldberg, D.E., Yassine, A., & Chen, Y.-P. ( 2003). A genetic algorithm design inspired by organization theory: a pilot study of a dependency structure matrix driven genetic algorithm . In E. Cantú-Paz (Ed.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2003), LNCS 2724 (pp. 1620-1621). Berlin: Springer-Verlag .
