Self-Organization Driven by Internally-Generated Patterns
Active from 1997 - 2002
Work with the RF-LISSOM model has shown that it can develop realistic cortical structures when presented with approximations of the visual environment. However, the brain already has significant structure at birth, so environmental inputs cannot account for all of this self-organization. This ongoing research project explores a surprisingly simple but very effective way that an organism's genome can specify detailed cortical structures by generating training patterns internally.
James A. Bednar Postdoctoral Alumni jbednar [at] inf ed ac uk
Prenatal and Postnatal Development of Laterally Connected Orientation Maps 2004
James A. Bednar and Risto Miikkulainen, Neurocomputing, Vol. 58-60 (2004), pp. 985-992.
Learning Innate Face Preferences 2003
James A. Bednar and Risto Miikkulainen, Neural Computation, Vol. 15, 7 (2003), pp. 1525-1557.
Learning to See: Genetic and Environmental Influences on Visual Development 2002
James A. Bednar, PhD Thesis, Department of Computer Sciences, The University of Texas at Austin. Also Technical Report AI-TR-02-294.

The LISSOM package contains the C++, Python, and Scheme source code and examples for training and testing firing-rate...