UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
General Intelligence through Prolonged Evolution of Densely Connected Neural Networks (2014)
Padmini Rajagopalan
,
Aditya Rawal
,
Kay E. Holekamp
and
Risto Miikkulainen
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.
View:
PDF
Citation:
In
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014)
, Vancouver, BC, Canada, July 2014.
Bibtex:
@inproceedings{rajagopalan:gecco2014, title={General Intelligence through Prolonged Evolution of Densely Connected Neural Networks}, author={Padmini Rajagopalan and Aditya Rawal and Kay E. Holekamp and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014)}, month={July}, address={Vancouver, BC, Canada}, url="http://www.cs.utexas.edu/users/ai-lab?rajagopalan:gecco2014", year={2014} }
People
Kay E. Holekamp
Formerly affiliated 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
Projects
The Role of Emotion and Communication in Cooperative Behavior
2013 - 2016
Areas of Interest
Artificial Life
Cognitive Science
Evolutionary Computation
Neuroevolution
Demos
Cooperation to Overcome a More Powerful Adversary
Kay Holekamp
2012
Labs
Neural Networks