Attractor Landscapes and Active Tracking: The Neurodynamics of Embodied Action

Abstract

Behavior is the product of three intertwining dynamics: of the world, of the body and of internal control structures. Neurodynamics focuses on the dynamics of neural control, while observing interfaces with the world and the body. From this perspective, we present a dynamical analysis of embodied recurrent neural networks evolved to control a cybernetic device that solves a problem in active tracking. For competent action selection, agents must rely on the attractor landscapes of the evolved networks. Insights into how the networks achieve this are given in terms of the network's dynamical substrate, which highlights the role of the network's inherent attractors as they change as a function of the input parameters (sensors). We introduce some terminological extensions to neurodynamics to allow for a more precise formulation of how attractor changes influence behavior generation: in particular, attractor landscapes, which are the space of all attractors accessible through coherent parametrizations of the network (input stimuli), and the meta-transient, which resolves behavior by approaching attractors as they shape-shift. We apply these concepts to the analysis of interesting behaviors of the tracking device, such as temporal contextual dependency, chaotic transitory regimes in moments of ambiguity, and implicit mapping of environmental asymmetricities in the response of the device. Finally, we discuss the relevance of the concepts introduced in terms of autonomy, learning, and modularity.

Keywords

neurodynamics dynamical systems active tracking chaos recurrent neural networks cognition

Get full access to this article

View all access options for this article.

References

Banerjee, A. (2001). The roles played by external input and synaptic modulations in the dynamics of neuronal systems. Behavioral and Brain Sciences, 24(5), 811—812.

Beer, R. (1995). A dynamical systems perspective on agent— environment interaction. Artificial Intelligence, 72(1), 173—215.

Beer, R.D. (2006). Parameter space structure of continuous-time recurrent neural networks. Neural Computation, 18, 3009—3051.

Beer, R. (2008). Beyond control: The dynamics of brain—body— environment interaction in motor systems. In D. Sternad (Ed.), Progress in motor control: A multidisciplinary perspective. Berlin: Springer.

Beer, R. , & Gallagher, J. (1992). Evolving dynamical neural networks for adaptive behavior. Adaptive Behavior, 1(1), 91—122.

Berry, H. , & Quoy, M. (2006). Structure and dynamics of random recurrent neural networks. Adaptive Behavior, 14(2), 129—137.

Clark, A. , & Chalmers, D. (1998). The extended mind. Analysis, 58(1), 7—19.

Dieckmann, U. (1995). Coevolution as an autonomous learning strategy for neuromodules. In H. J. Herrmann , D. Wolf , & E. Pöppel (Eds.), Supercomputing in brain research: From tomography to neural networks (pp. 427—432). Singapore: World Scientific.

Fodor, J.A. (1983). The modularity of mind. Cambridge, MA: MIT Press.

10.

Freeman, W. (1995). Society of brains: A study in the neuro-science of love and hate. Philadelphia, PA: Lawrence Erlbaum.

11.

Grush, R. (2004). The emulation theory of representation: Motor control, imagery and perception. Behavioral and Brain Sciences , 27, 377—442.

12.

Harvey, I. , Di Paolo, E. , Wood, R. , Quinn, M. , & Tuci, E. (2005). Evolutionary robotics: A new scientific tool for studying cognition. Artificial Life, 11(1—2), 79—98.

13.

Haugeland, J. (1995). Mind embodied and embedded. Acta Philosophica Fennica, 58, 233—267.

14.

Huelse, M. , Wischmann, S. , & Pasemann, F. (2004). Structure and function of evolved neuro-controllers for autonomous robots. Connection Science, 16(4), 249—266.

15.

Husbands, P. , Harvey, I. , & Cliff, D. (1993). Analysing recurrent dynamical networks evolved for robot control. In Proceedings of the 3rd IEE International Conference on Artificial Neural Networks (ANN93) (pp. 158—162). London: IEE Press.

16.

Ikegami, T. , & Tani, J. (2001). Chaotic itinerancy needs embodied cognition to explain memory dynamics. Behavioral and Brain Sciences, 24(5), 818—819.

17.

Ijspeert, A.J. , Nakanishi, J. , & Schaal, S. (2003). Learning attractor landscapes for learning motor primitives. In S. Becker , S. Thrun , & K. Obermayer (Eds.), Advances in neural information processing systems 15. Cambridge, MA: MIT Press.

18.

Jaegger, H. , Maas, W. , & Markram, H. (2007). 2007 special issue: Echo state networks and liquid state machines. Neural Networks, 20(3), 290—297.

19.

Kaneko, K. (1990). Clustering, coding, switching, hierarchical ordering, and control in network of chaotic elements. Physica D, 41, 137—172.

20.

Kaneko, K. , & Tsuda, I. (2003). Chaotic itinerancy. Chaos, 13(3), 926—936.

21.

Merleau-Ponty, M. (1965). The structure of behavior. London: Methuen.

22.

Molter, C. , Salihoglu, U. , & Bersini, H. (2007). The road to chaos by time-asymmetric Hebbian learning in recurrent neural networks. Neural Computation, 19, 80—110.

23.

Negrello, M. , & Pasemann, F. (2008). Adaptive neurodynamics. In Y. Shan & A. Yang (Eds.), Applications of complex adaptive systems. Hershey, PA: IGI Publishing.

24.

Pasemann, F. (1995). Neuromodules: A dynamical systems approach to brain modelling. In H. J. Herrmann , D. Wolf , & E. Pöppel (Eds.), Supercomputing in brain research: From tomography to neural networks (pp. 331—347). Singapore: World Scientific.

25.

Pasemann, F. (2002). Complex dynamics and the structure of small neural networks. Network: Computation in Neural Systems, 13(2), 195—216.

26.

Pasemann, F. , Steinmetz, U. , Hülse, M. , & Lara, B. (2001). Robot control and the evolution of modular neurodynamics . Theory in Biosciences, 120, 311—326.

27.

Philipona, D. , O'Regan, J.K. , Nadal, J.-P. , & Coenen, O.J.-M.D. (2003). Perception of the structure of the physical world using unknown multimodal sensors and effectors. In S. Thrun , L. K. Saul , & B. Schölkopf (Eds.), Advances in neural information processing systems 16. Cambridge, MA: MIT Press.

28.

Simon, H. (1969). The sciences of the artificial. Cambridge, MA: MIT Press.

29.

Sterelny, K. (2005). Thought in a hostile world. Cambridge, MA: MIT Press.

30.

Tani, J. (1998). An interpretation of the “self” from the dynamical systems perspective: A constructivist approach. Journal of Consciousness Studies, 5(5—6), 516—542.

31.

Tsuda, I. (1991). Chaotic itinerancy as a dynamical basis of hermeneutics in brain and mind. In Microcomputers and attention. Manchester, UK: Manchester University Press.

32.

Tsuda, I. (2001). Toward an interpretation of dynamic neural activity in terms of chaotic dynamical systems. Behavioral and Brain Sciences, 24, 793—847.

33.

Varela, F. (1979). Principles of biological autonomy. Amsterdam: North-Holland.

34.

von Holst, V.E. , & Mittelstaedt, H. (1950). Das reafferenzprinzip (wechselwirkung zwischen zentralnervensystem und peripherie). Naturwissenschaften, 37, 464—476.

35.

Watson, R.A. , & Pollack, J.B. (2005). Modular interdependency in complex dynamical systems . Artificial Life, 11(4), 445—457.