Abstract
What is time? Since the function of the brain is closely tied in with that of time, investigating the origin of time in the brain can help shed light on this question. In this paper, we propose to use simulated evolution of artificial neural networks to investigate the relationship between time and brain function, and the evolution of time in the brain. A large number of neural network models are based on a feedforward topology (perceptrons, backpropagation networks, radial basis functions, support vector machines, etc.), thus lacking dynamics. In such networks, the order of input presentation is meaningless (i.e., it does not affect the behavior) since the behavior is largely reactive. That is, such neural networks can only operate in the present, having no access to the past or the future. However, biological neural networks are mostly constructed with a recurrent topology, and recurrent (artificial) neural network models are able to exhibit rich temporal dynamics, thus time becomes an essential factor in their operation. In this paper, we will investigate the emergence of recollection and prediction in evolving neural networks. First, we will show how reactive, feedforward networks can evolve a memory-like function (recollection) through utilizing external markers dropped and detected in the environment. Second, we will investigate how recurrent networks with more predictable internal state trajectory can emerge as an eventual winner in evolutionary struggle when competing networks with less predictable trajectory show the same level of behavioral performance. We expect our results to help us better understand the evolutionary origin of recollection and prediction in neuronal networks, and better appreciate the role of time in brain function.
This chapter is largely based on “Evolution of Recollection and Prediction in Neural Networks”, by J.R. Chung, J. Kwon and Y. Choe, which appeared in the Proceedings of the International Joint Conference on Neural Networks, 571–577, IEEE Press, 2009.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Anderson CW (1989) Learning to control an inverted pendulum using neural networks. IEEE Control Syst Mag 9:31–37
Balch T (1993) Avoiding the past: a simple but effective strategy for reactive navigation. In: Proceedings of the 1993 IEEE international conference on robotics and automation. IEEE, New York, pp 678–685
Beer RD (2000) Dynamical approaches to cognitive science. Trends Cogn Sci 4:91–99
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Chalmers DJ (1996) The conscious mind: in search of a fundamental theory. Oxford University Press, New York
Chandrasekharan S, Stewart T (2004) Reactive agents learn to add epistemic structures to the world. In: Forbus KD, Gentner D, Regier T (eds) CogSci2004. Lawrence Erlbaum, Hillsdale
Chandrasekaran S, Stewart TC (2007) The origin of epistemic structures and proto-representations. Adapt Behav 15:329–353
Choe Y, Miikkulainen R (2004) Contour integration and segmentation in a self-organizing map of spiking neurons. Biol Cybern 90:75–88
Chung JR, Choe Y (2009) Emergence of memory-like behavior in reactive agents using external markers. In: Proceedings of the 21st international conference on tools with artificial intelligence, 2009, ICTAI ’09, pp 404–408
Chung JR, Kwon J, Choe Y (2009) Evolution of recollection and prediction in neural networks. In: Proceedings of the international joint conference on neural networks. IEEE Press, Piscataway, pp 571–577
Clark A (2008) Supersizing the mind: embodiement, action, and cognition. Oxford University Press, Oxford
Conover MR (2007) Predator-prey dynamics: the role of olfaction. CRC Press, Boca Raton
Elman JL (1990) Finding structure in time. Cogn Sci 14:179–211
Elman JL (1991) Distributed representations, simple recurrent networks, and grammatical structure. Mach Learn 7:195–225
Felleman DJ, Essen DCV (1991) Distributed hierarchical processing in primate cerebral cortex. Cereb Cortex 1:1–47
Frisén J, Johansson CB, Lothian C, Lendahl U (1998) Central nervous system stem cells in the embryo and adult. Cell Mol Life Sci 54:935–945
Gomez F, Miikkulainen R (1998) 2-D pole-balancing with recurrent evolutionary networks. In: Proceedings of the international conference on artificial neural networks. Springer, Berlin, pp 425–430
Hawkins J, Blakeslee S (2004) On intelligence, 1st edn. Henry Holt and Company, New York
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall, Upper Saddle River
Hildebrand JG (1995) Analysis of chemical signals by nervous systems. Proc Natl Acad Sci USA 92:67–74
Krichmar JL (2008) The neuromodulatory system: a framework for survival and adaptive behavior in a challenging world. Adapt Behav 16:385–399
Kwon J, Choe Y (2007) Enhanced facilitatory neuronal dynamics for delay compensation. In: Proceedings of the international joint conference on neural networks. IEEE Press, Piscataway, pp 2040–2045
Kwon J, Choe Y (2008) Internal state predictability as an evolutionary precursor of self-awareness and agency. In: Proceedings of the seventh international conference on development and learning. IEEE, New York, pp 109–114
Kwon J, Choe Y (2009) Facilitating neural dynamics for delay compensation: a road to predictive neural dynamics? Neural Netw 22:267–276
Lim H, Choe Y (2005) Facilitatory neural activity compensating for neural delays as a potential cause of the flash-lag effect. In: Proceedings of the international joint conference on neural networks. IEEE Press, Piscataway, pp 268–273
Lim H, Choe Y (2006) Compensating for neural transmission delay using extrapolatory neural activation in evolutionary neural networks. Neural Inf Process, Lett Rev 10:147–161
Lim H, Choe Y (2006) Delay compensation through facilitating synapses and STDP: a neural basis for orientation flash-lag effect. In: Proceedings of the international joint conference on neural networks. IEEE Press, Piscataway, pp 8385–8392
Lim H, Choe Y (2006) Facilitating neural dynamics for delay compensation and prediction in evolutionary neural networks. In: Keijzer M (ed) Proceedings of the 8th annual conference on genetic and evolutionary computation, GECCO-2006, pp 167–174
Lim H, Choe Y (2008) Delay compensation through facilitating synapses and its relation to the flash-lag effect. IEEE Trans Neural Netw 19:1678–1688
Llinás RR (2001) I of the vortex. MIT Press, Cambridge
Machold R, Hayashi S, Rutlin M, Muzumdar MD, Nery S, Corbin JG, Gritli-Linde A, Dellovade T, Porter JA, Rubin SL, Dudek H, McMahon AP, Fishell G (2003) Sonic hedgehog is required for progenitor cell maintenance in telencephalic stem cell niches. Neuron 39:937–950
Mackie GO (2003) Central circuitry in the jellyfish aglantha digitale iv. pathways coordinating feeding behaviour. J Exp Biol 206:2487–2505
Mann TA, Choe Y (2010) Neural conduction delay forces the emergence of predictive function in an evolving simulation. BMC Neurosci 11(Suppl 1):P62. Nineteenth annual computational neuroscience meeting: CNS*2010
Miikkulainen R, Bednar JA, Choe Y, Sirosh J (2005) Computational maps in the visual cortex. Springer, Berlin. URL: http://www.computationalmaps.org
Palma V, Lim DA, Dahmane N, Sánchez P, Brionne TC, Herzberg CD, Gitton Y, Carleton A, Álvarez Buylla A, Altaba AR (2004) Sonic hedgehog controls stem cell behavior in the postnatal and adult brain. Development 132:335–344
Peck C, Kozloski J, Cecchi G, Hill S, Schürmann F, Markram H, Rao R (2008) Network-related challenges and insights from neuroscience. Lect Notes Comput Sci 5151:67–78
Rocha LM (1996) Eigenbehavior and symbols. Syst Res 13:371–384
Rosen R (1985) Anticipatory systems: philosophical, mathematical and methodological foundations. Pergamon, New York
Stanley KO, Miikkulainen R (2002) Efficient evolution of neural network topologies. In: Proceedings of the 2002 congress on evolutionary computation (CEC’02). IEEE, Piscataway
Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10:99–127
Tillman JA, Seybold SJ, Jurenka RA, Blomquist GJ (1999) Insect pheromones—an overview of biosynthesis and endocrine regulation. Insect Biochem Mol Biol 29:481–514
Turvey MT, Shaw R (1979) The primacy of perceiving: an ecological reformulation of perception for understanding memory. In: Nilsson L-G (ed) Perspectives on memory research: essays in honor of Uppsala University’s 500th anniversary. Chap. 9. Lawrence Erlbaum Associates, Hillsdale, pp 167–222
Vanderhaeghen P, Schurmans S, Vassart G, Parmentier M (1997) Specific repertoire of olfactory receptor genes in the male germ cells of several mammalian species. Genomics 39:239–246
von der Malsburg C, Buhmann J (1992) Sensory segmentation with coupled neural oscillators. Biol Cybern 67:233–242
Ward R, Ward R (2006) 2006 special issue: cognitive conflict without explicit conflict monitoring in a dynamical agent. Neural Netw 19(9):1430–1436
Wood DL (1982) The role of pheromones, kairomones, and allomones in the host selection and colonization behavior of bark beetles. Annu Rev Entomol 27:411–446
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Chung, J.R., Kwon, J., Mann, T.A., Choe, Y. (2012). Evolution of Time in Neural Networks: From the Present to the Past, and Forward to the Future. In: Rao, A., Cecchi, G. (eds) The Relevance of the Time Domain to Neural Network Models. Springer Series in Cognitive and Neural Systems, vol 3. Springer, Boston, MA. https://doi.org/10.1007/978-1-4614-0724-9_6
Download citation
DOI: https://doi.org/10.1007/978-1-4614-0724-9_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4614-0723-2
Online ISBN: 978-1-4614-0724-9
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)