Abstract.
This paper is a presentation of neuronal control systems in the terms of the dynamical systems theory, where (1) the controller and its surrounding environment are seen as two co-dependent controlled dynamical systems (2) the behavioral transitions that take place under adaptation processes are analyzed in terms of phase-transitions. We present in the second section a generic method for the construction of multi-population random recurrent neural networks. The third section gives an overview of the various phase transitions that take place under an external forcing signal, or under internal parametric changes. The section 4 presents some applications in the domain of sequence identification and active perception modeling. The section 5 presents some applications in the domain of closed-loop control systems and reinforcement learning.
Similar content being viewed by others
References
S. Grossberg, Proc. Natl. Acad. Sci. USA 59, 368–371 (1968)
S. Amari, IEEE Trans. Syst. Man. Cyb. SMC-2, 643–657 (1972)
J. Hopfield, Proc. Nat. Acad. Sci. 79, 2554–2558 (1982)
G.A. Carpenter, S. Grossberg, Comput. Vis. Graph. Image Process. 37, 54–115 (1987)
C. Skarda, W. Freeman, Behav. Brain Sci. 10, 161–195 (1987)
M.A. Cohen, S. Grossberg, IEEE Trans. Syst. Man. Cybern. SMC13, 815–826 (1983)
S. Amari, IEEE Trans. Comp. C-21, 1197–1206 (1972)
H. Sompolinsky, I. Kanter, Phys. Rev. Lett. USA 57, 2861–2864 (1986)
S. Dehaene, J.-P. Changeux, J.-P. Nadal, Proc. Natl. Acad. Sci. USA 84, 2727–2731 (1987)
F. Delcomyn, Science 210, 492–498 (1980)
P. Meyrand, J. Simmers, M. Moulins, Nature 351, 60–63 (1991)
R. Rao, T. Sejnowski, Neural Comput. 13, 2221–2237 (2001)
C. Leibold, R. Kempter, Neural Comput. 18, 904–941 (2006)
E. Rodriguez, N. George, J.-P. Lachaux, J. Martinerie, B. Renault, F. Varela, Nature 397, 430–433 (1999)
B. Ans, Y. Coiton, J.-C. Gilhodes, J.-L. Velay, Neural Netwo. 7, 1461–1476 (1994)
E. Bicho, G. Schöner, Robot. Auton. Syst. 21, 23–35 (1997)
S. Haykin, Neural Networks: A Comprehensive Fundation (Prentice-Hall, 1999)
G. Dreyfus, J.-M. Martinez, M. Samuelides, M.B. Gordon, F. Badran, S. Thiria, L. Hérault, Réseaux de neurones - Méthodologie et applications (Eyrolles, Paris, 2002)
M. Ghallab, D. Nau, P. Traverso, Automated Planning, Theory and Practice (Elsevier, Morgan-Kaufmann, 2004)
J.J. Gibson, The Ecological Approach to Visual Perception (Houghton-Mifflin, Boston, 1979)
R. Brooks, Artific. Intell. 47, 139–159 (1991)
K. O'Regan, G. Noë, Behav. Brain Sci. (2001)
R. Sutton, Mach. Learn. 3, 9–44 (1988)
K. Doya, Neural Comput. 12, 219–245 (2000)
C. Watkins, P. Dayan, Mach. Learn. 8, 279–292 (1992)
R.J. Williams, Mach. Learn. 8, 229–256 (1992)
P. Bartlett, J. Baxter, Hebbian synaptic modifications in spiking neurons that learn, School of Information Science and Engineering, Australian National University, Tech. Rep. (1999)
H. Tuckwell, Introduction to Theoretical Neurobiology (Cambridge University Press, 1988)
A. Herz, B. Sulzer, R. Kuhn, J.L. van Hemmen, Biol. Cybern. 60, 457–467 (1989)
D. Hebb, The Organization of Behavior (Wiley, New York, 1949)
G. Turrigiano, K. Leslie, N. Desai, L. Rutherford, S. Nelson, Nature 391, 892–896 (1998)
T.J. Sejnowski, J. Math. Biol. 4, 303–321 (1977)
T.V.P. Bliss, T. Lomo, J. Physiol. 232, 331–356 (1973)
H. Markram, J. Lubke, M. Frotscher, B. Sakmann, Science 275, 213–215 (1997)
G.-Q. Bi, M.-M. Poo, J. Neurosci. 18, 10464–10472 (1998)
S. Song, K. Miller, L. Abbott, Nat. Neurosci. 3, 919–926 (2000)
H. Sompolinsky, A. Crisanti, H. Sommers, Phys. Rev. Lett. 61, 259–262 (1988)
B. Cessac, J. Phys. I (France) 5, 409–432 (1995)
B. Doyon, B. Cessac, M. Quoy, M. Samuelides, Int. J. Bif. Chaos 3, 279–291 (1993)
S. Grossberg, Biol. Cybern. 23, 121–134, 196–202 (1976)
S. Amari, Biol. Cybern. 27, 77–87 (1977)
T. Kohonen, Biol. Cybern. 43, 59–69 (1982)
G. Schöner, M. Dose, C. Engels, Robot. Auton. Syst. 16, 213–245 (1995)
S. Moga, P. Gaussier, A neuronal structure for learning by imitation, in Lecture Notes in Artificial Intelligence – European Conference on Artificial Life, edited by D. Floreano, J.-D. Nicoud, F. Mondada (Lausanne, 1999), pp. 314–318
S. Funahashi, C.J. Bruce, P.S. Goldman-Rakic, J. Neurophysiol. 61, 331–349 (1989)
R. Ben-Yishai, R. Lev Bar-Or, H. Sompolinsky, Proc. Natl. Acad. Sci. USA 92, 3844–3848 (1995)
R. Ben-Yishai, D. Hansel, H. Sompolinsky, J. Comput. Neurosci. 4, 57–79 (1997)
D. Hansel, H. Sompolinsky, J. Comput. Neurosci. 3, 7–34 (1996)
M. Camperi, X.-J. Wang, J. Comput. Neurosci. 5, 383–405 (1998)
Wang, J. Neurosci. 19, 9587–9603 (1999)
A. Compte, N. Brunel, P.S. Goldman-Rakic, X.-J. Wang, Cerebr. Cortex 10, 910–923 (2000)
A.D.E. Guillot, Approche Dynamique de la Cognition Artificielle (Lavoisier, 2002)
M. Adachi, A. Kazuyuki, Neural Netw. 10, 83–98 (1997)
I. Tsuda, Neural Netw. 5, 313–326 (1992)
U. Riedel, R. Kuhn, J. Van Hemmen, Phys. Rev. A 38, 1105–1108 (1988)
K. Ntzel, J. Kien, K. Bauer, J. Altman, U. Krey, Biol. Cybern. 70, 553–561 (1994)
O. Hoshino, Y. Kashimori, T. Kambara, Biol. Cybern. 79, 109–120 (1998)
S. Amari, Kybernetik 14, 201–215 (1974)
W. Gerstner, R. Ritz, L. Van Hemmen, Biol. Cybern. 68, 363–374 (1993)
N. Brunel, V. Hakim, Neural Comput. 11, 1621–1676 (1999)
E. Daucé, O. Moynot, O. Pinaud, M. Samuelides, Neural Proc. Lett. 14, 115–126 (2001)
I Ginzburg, H. Sompolinsky, Phys. Rev. E. 50, 3171–3191 (1994)
O. Moynot, M. Samuelides, PTRF 123, 41–75 (2002)
C. Van Vreeswijk, H. Sompolinsky, Neural Comput. 10, 1321–1371 (1998)
E. Daucé, O. Moynot, O. Pinaud, M. Samuelides, B. Doyon, Mean field equations reveal synchronization in a 2-populations neural network model, in ESANN 99, edited by M. Verleysen (D-Facto, 1999), pp. 7–12
P. Bush, T. Sejnowski, J. Comput. Neurosci. 3, 91–110 (1996)
E.M. Izhikevich, IEEE Trans. Neural Netw. 14, 1569–1572 (2003)
E. Daucé, M. Quoy, B. Cessac, B. Doyon, M. Samuelides, Neural Networks 11, 521–533 (1998)
W. Singer, Time as coding space in neocortical processing: a hypothesis, in Temporal Coding in the Brain, edited by G. Buzsáki (Springer-Verlag, Berlin, Heidelberg, 1994), pp. 51–79
N. Brunel, X.-J. Wang, J. Comput. Neurosci. 11, 63–85 (2001)
A. Penn, Steps towards a quantitative analysis of individuality and its maintenance: a case study with multi-agent systems, in Fifth German Workshop on Artificial Life: Abstracting and Synthesizing the Principles of Living Systems, edited by D. Polani, J. Kim, T. Martinez (IOS Press, 2002), pp. 125–134
J. Tani, Model-based learning for mobile robot navigation from the dynamical system perspective, IEEE Trans. System, Man and Cybern. B 26, 421–436 (1996)
B. Kosko, Bidirectional associative memories, IEEE Trans. Systems, Man Cybern. 18, 49–60 (1988)
F. Varela, Principles of Biological Autonomy (North Holland, Amsterdam, 1979)
B. Brembs, F. Lorenzetti, F. Reyes, D. Baxter, J. Byrne, Science 296, 1706–1709 (2002)
J. Daphna, Y. Niv, E. Ruppin, Neural Networks 15, 535–547 (2002)
E. Daucé, Nat. Comp. 2, 135–157 (2004)
E. Daucé, Hebbian reinforcement learning in a modular dynamic network, in Proceedings of the Eighth International Conference on Simulation of Adaptive Behavior (SAB'04) (2004), pp. 305–314
B. Cessac, M. Samuelides, Eur. Phys. J. Special Topics 142, 7–88 (2007)
M. Samuelides, B. Cessac, Eur. Phys. J. Special Topics 142, 89–122 (2007)
L. Perrinet, Eur. Phys. J. Special Topics 142, 163–225 (2007)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Daucé, E. Learning and control with large dynamic neural networks. Eur. Phys. J. Spec. Top. 142, 123–161 (2007). https://doi.org/10.1140/epjst/e2007-00060-8
Issue Date:
DOI: https://doi.org/10.1140/epjst/e2007-00060-8