Skip to main content Accessibility help
  • Print publication year: 2010
  • Online publication date: July 2011

16 - Methodological issues in modelling ecological learning with neural networks

from Part IV - Methodological issues in the use of simple feedforward networks


16.1 Introduction

A key attribute of all but the simplest organisms is an ability to modify their actions in the light of experience – that is to learn. This attribute allows individuals to adapt to rapidly changing environments. Learning is a fundamental aspect of animal behaviour (Barnard, 2003). One aspect of animal behaviour where learning has been particularly extensively studied is food gathering (see recent reviews by Adams-Hunt & Jacobs, 2007; Sherry & Mitchell, 2007; Stephens, 2007), and it is this aspect that we will focus on. We use the term ecological learning to describe an organism learning about its environment.

Neural network models are being used increasingly as effective tools for the description and study of animal behaviour (see Enquist & Ghirlanda, 2005 for a review). There are many different techniques that can be used to model animal learning, with Bayesian approaches being one such example. However, with the desire of taking advantage of neural networks' ability to generalise, neural networks have also been used to model stimulus learning in animals, and have even been used to examine the difference between neural network predators that evolve or learn (for example, see Kamo et al., 2002). In this paper we focus solely on the use of neural networks to represent ecological learning (such as a predator learning and generalising over prey) and argue that there are fundamental differences between the way neural network models are generally trained and the way organisms learn.

Ackley, D. & Littman, M. 1991. Interactions between learning and evolution. In Artificial Life II. Studies in the Sciences of Complexity (ed. Langton, C. G., Taylor, C., Farmer, J. D., and Rasmussen, S.). Addison-Wesley.
Adams-Hunt, M. M. & Jacobs, L. F. 2007. Cognition for Foraging. In Foraging: Behaviour and Ecology (ed. Stephens, D., Brown, J. & Ydenberg, R.), pp. 105–140. Chicago University Press.
Baldwin, M. J. 1896. A new factor in evolution. Am Naturalist 30, 441–451.
Balogh, A. C. V. & Leimar, O. 2005. Müllerian mimicry: an examination of Fisher's theory of gradual evolutionary change. Proc R Soc B 272, 2269–2275.
Barnard, C. 2003. Animal Behaviour. Prentice Hall.
Barto, A. J. 1995. Reinforcement learning. In The Handbook of Brain Theory and Neural Networks (ed. Arbib, M.), pp. 804–809. MIT Press.
Enquist, M. & Ghirlanda, S. 2005. Neural Networks and Animal Behavior. Princeton University Press.
Fahlman, S. E. 1988. Faster-learning variations on back-propagation: an empirical study. Proceedings of the 1988 Connectionist Models Summer School. Morgan-Kaufmann.
Franks, D. W. & Noble, J. 2004. Warning signals and predator-prey coevolution. Proc R Soc B 271, 1859–1866.
Ghirlanda, S. & Enquist, M. 1998. Artificial neural networks as models of stimulus control. Anim Behav 56, 1383–1389.
Haas, B. A. 2006. Speciation by perception. Anim Behav 72, 139–146.
Ham, A. D., Ihalainen, E., Lindstrom, L. & Mappes, J. 2006. Does colour matter? The importance of colour in avoidance learning, memorability and generalisation. Behav Ecol Sociobiol 60, 482–491.
Hinton, G. E. & Nowlan, S. J. 1987. How learning can guide evolution. Complex Syst 1, 495–502.
Ihalainen, E., Lindstrom, , L. & Mappes, J. 2007. Investigating Mullerian mimicry: predator learning and variation in prey defences. J Evol Biol 20, 780–791.
Kamo, M., Ghirlanda, , S. & Enquist, M. 2002. The evolution of signal form: effects of learned versus inherited recognition. Proc R Soc B 269, 1765–1771.
Mazzoni, P., Andersen, , R. A. & Jordan, M. I. 1991. A more biologically plausible learning rule for neural networks. Proc Natl Acad Sci US A 88, 4433–4437.
Riedmiller, M. & Braun, H. 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks.
Ruxton, G. D., Sherratt, T. N. & Speed, M. P. 2004. Avoiding Attack: The Evolutionary Ecology of Crypsis, Warning Signals and Mimicry. Oxford University Press.
Sherry, D. F. & Mitchell, J. B. 2007. Neuroethology of foraging. In Foraging: Behaviour and Ecology (ed. Stephens, D., Brown, J., and Ydenberg, R.), pp. 61–104. Chicago University Press.
Shettleworth, S. J. 1998. Cognition, Evolution and Behaviour. Oxford University Press.
Skelhorn, J. & Rowe, C. 2005. Frequency-dependent taste-rejection by avian predation may select for defence chemical polymorphisms in aposematic prey. Biol Lett 1, 500–503.
Skelhorn, J. & Rowe, C. 2006a. Avian predators taste-reject aposematic prey on the basis of their chemical defence. Biol Lett 2, 348–350.
Skelhorn, J. & Rowe, C. 2006b. Prey palatability influences predator learning and memory. Anim Behav 71, 1111–1118.
Stephens, D. W. 2007. Models of information use. In Foraging: Behaviour and Ecology (ed. Stephens, D., Brown, J. & Ydenberg, R.), pp. 31–60. Chicago University Press.
Toquenaga, Y., Kajitani, , I. & Hoshino, T. 1995. Egrets of a feather flock together. Artific Life 1, 391–411.