Constructing good learners using evolved pattern generators

ABSTRACT

Self-organization of brain areas in animals begins prenatally, evidently driven by spontaneously generated internal patterns. The neural structures continue to develop postnatally when the sensory systems are exposed to stimuli from the environment. In this process, prenatal training may give the neural system the appropriate bias so that it can learn reliably under changing environmental stimuli. This paper evaluates the hypothesis that an artificial learning system can benefit from a similar approach, consisting of initial training with patterns from an evolved generator followed by training with the actual training set. Competitive learning networks were trained in recognizing handwritten digits in three ways: through environmental learning only, through evolution only, and through prenatal training with evolved pattern generators followed by environmental learning. The results demonstrate that the evolved pattern generator approach leads to better learning performance, suggesting that complex systems can be constructed effectively in this way.

References

1. J. M. Baldwin. A new factor in evolution. The American Naturalist, 30:441--451, 536--553, 1896.
2. H. B. Barlow. Unsupervised learning. Neural Computation, 1:295--311, 1989.
3. J. A. Bednar and R. Miikkulainen. Learning innate face preferences. Neural Computation, 15(7):1525--1557, 2003.
4. J. A. Bednar and R. Miikkulainen. Constructing visual function through prenatal and postnatal learning. In D. Mareschal, M. H. Johnson, S. Sirois, M. Spratling, M. S. C. Thomas, and G. Westermann, editors, Neuroconstructivism, Vol. 2: Perspectives and Prospects. Oxford University Press, Oxford, UK, 2005. In press.
5. C. Blakemore and G. F. Cooper. Development of the brain depends on the visual environment. Nature, 228:477--478, 1970.
6. C. Blakemore and R. C. van Sluyters. Innate and environmental factors in the development of the kitten's visual cortex. The Journal of Physiology, 248:663--716, 1975.
7. M. Catsicas and P. Mobbs. Waves are swell. Current Biology, 5(9):977--979, 1995.
8. M. C. Crair, D. C. Gillespie, and M. P. Stryker. The role of visual experience in the development of columns in cat visual cortex. Science, 279:566--570, 1998.
9. J. L. Elman, E. A. Bates, M. H. Johnson, A. Karmiloff-Smith, D. Parisi, and K. Plunkett. Rethinking Innateness: A Connectionist Perspective on Development. MIT Press, Cambridge, MA, 1996.
10. M. B. Feller, D. P. Wellis, D. Stellwagen, F. S. Werblin, and C. J. Shatz. Requirement for cholinergic synaptic transmission in the propagation of spontaneous retinal waves. Science, 272:1182--1187, 1996.
11. S. Geman, E. L. Bienenstock, and R. Doursat. Neural networks and the bias/variance dilemma. Neural Computation, 4(1):1--58, 1992.
12. S. Grossberg. Competitive learning: From interactive activation to adaptive resonance. Cognitive Science, 11:23--63, 1987.
13. S. Haykin. Neural Networks, A Comprehensive Foundation. Prentice Hall, Upper Saddle River, New Jersey, 1999.
14. D. O. Hebb. The Organization of Behavior: A Neuropsychological Theory. Wiley, Hoboken, NJ, 1949.
15. G. E. Hinton and S. J. Nowlan. How learning can guide evolution. Complex Systems, 1:495--502, 1987.
16. D. H. Hubel and T. N. Wiesel. Sequence regularity and geometry of orientation columns in the monkey striate cortex. The Journal of Comparative Neurology, 158:267--294, 1974.
17. D. H. Hubel, T. N. Wiesel, and S. LeVay. Plasticity of ocular dominance columns in monkey striate cortex. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 278:377--409, 1977.
18. T. Kohonen. Self-Organizing Maps. Springer, Berlin, 1995.
19. L. Maffei and L. Galli-Resta. Correlation in the discharges of neighboring rat retinal ganglion cells during prenatal life. Proceedings of the National Academy of Sciences, USA, 87:2861--2864, 1990.
20. G. A. Marks, J. P. Shaffery, A. Oksenberg, S. G. Speciale, and H. P. Roffwarg. A functional role for REM sleep in brain maturation. Behavioural Brain Research, 69:1--11, 1995.
21. M. Meister, R. O. L. Wong, D. A. Baylor, and C. J. Shatz. Synchronous bursts of action-potentials in the ganglion cells of the developing mammalian retina. Science, 252:939--943, 1991.
22. R. Miikkulainen, J. A. Bednar, Y. Choe, and J. Sirosh. Computational Maps in the Visual Cortex. Springer, Berlin, 2005. In press.
23. J. A. Movshon and R. C. van Sluyters. Visual neural development. Annual Review of Psychology, 32:477--522, 1981.
24. S. Nolfi, J. L. Elman, and D. Parisi. Learning and evolution in neural networks. Adaptive Behavior, 2:5--28, 1994.
25. M. J. O'Donovan. The origin of spontaneous activity in developing networks of the vertebrate nervous system. Current Opinion in Neurobiology, 9:94--104, 1999.
26. D. E. Rumelhart and D. Zipser. Feature discovery by competitive learning. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations, pages 151--193. MIT Press, 1987.
27. F. Sengpiel and P. C. Kind. The role of activity in development of the visual system. Current Biology, 12(23):R818--R826, 2002.
28. C. J. Shatz. Impulse activity and the patterning of connections during CNS development. Neuron, 5:745--756, December 1990.
29. C. J. Shatz. The developing brain. Scientific American, 267(3):61--67, 1992.
30. C. J. Shatz. Emergence of order in visual system development. Proceedings of the National Academy of Sciences, USA, 93:602--608, 1996.
31. A. Slater and S. P. Johnson. Visual sensory and perceptual abilities of the newborn: Beyond the blooming, buzzing confusion. In F. Simion and G. Butterworth, editors, The Development of Sensory, Motor and Cognitive Capacities in Early Infancy: From Perception to Cognition, pages 121--142. Psychology Press, East Sussex, UK, 1998.
32. P. Utgoff and T. Mitchell. Acquisition of appropriate bias for inductive concept learning. In Proceedings of the Second National Conference on Artificial Intelligence, pages 414--417, Menlo Park, CA, 1982. AAAI Press.
33. R. O. L. Wong. Retinal waves and visual system development. Annual Review of Neuroscience, 22:29--47, 1999.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Knowledge representation and reasoning

      • Cognitive robotics

    • Philosophical/theoretical foundations of artificial intelligence

      • Cognitive science

  • Machine learning

    • Learning paradigms

      • Supervised learning

        • Supervised learning by classification

    • Machine learning approaches

      • Classification and regression trees

      • Neural networks