General Intelligence through Prolonged Evolution of Densely Connected Neural Networks (2014)
Different species of animals have vast differences in how general their learning abilities and behaviors are. This paper analyzes the effect of network connection density and prolonged evolution on general intelligence. Using the NEAT algorithm for neuroevolution, network structures with different connectivities were evaluated in recognizing digits and their mirror images. These experiments show that general intelligence, i.e. recognition of previously unseen examples, increases with increase in connectivity. General intelligence also increases with the number of generations in prolonged evolution, even when performance no longer improves in the known examples. This outcome suggests that general intelligence depends on specific anatomical and environmental factors.
In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014), Vancouver, BC, Canada, July 2014.

Kay E. Holekamp Collaborator holekamp [at] msu edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Padmini Rajagopalan Postdoctoral Alumni padminir [at] utexas edu
Aditya Rawal Ph.D. Alumni aditya [at] cs utexas edu