It has been reported recently that learning has a beneficial effect on evolution even if the learning involved the acquisition of an ability which is different from the ability for which individuals were selected (Nolfi, Elman & Parisi, 1994). This effect was explained as the result of the inter action between learning and evolution. In a successive paper, however, the effect was explained as a form of recovery from weight perturbation caused by mutations (Harvey, 1996, 1997). In this paper, I provide additional data that show how the effect, at least in the case considered in the paper, can only be explained as a result of the interaction between learning and evolution as originally hypothesized.
Harvey, I. (1996). Relearning and evolution in neural networks, Adaptive Behavior, 4(1), 81-84.
2.
Harvey, I. (1997). Is there another new factor in evolution ?, Evolutionary Computation, 4 (3), 313-329.
3.
Harvey, I. & Stone, J.V. (1996). Unicycling helps your French: spontaneous recovery of associations by learning unrelated tasks. Neural Computation , 8, 697-704.
4.
Hinton, G. & Plaut, D. (1987). Using fast weights to deblur old memories. In Proceedings of the 7th Annual Confermces of the Cognitive Science Society, Seattle, U.S.A
5.
Mayley, G. (1997). Landscapes, learning costs, and genetic assimilation , Evolutionary Computation, 4 (3), 213-234.
6.
Nolfi, S., Elman, J.L. & Parisi, D. (1994). Learning and evolution in neural networks. Adaptive Behavior, 1 (3), 5-28.
7.
Parisi, D. & Nolfi, S. (1996). How learning can influence evolution within a non-Lamarckian framework. In R.K. Belew, & M. Mitchell, (Eds.), Adaptive Individuals in Evolving Populations. SFI Studies in the Science of Complexity , Vol. XXVI. Boston, MA: Addison-Wesley.
8.
Parisi, D., Nolfi, S. & Cecconi, F. (1992). Learning, behavior and evolution. In F. Varela, & P. Bourgine , (Eds.), Toward a Practice of Autonomous Systems. Cambridge, MA: MIT Press.
