Abstract
In recent years there have been many works describing successful autonomous agents controlled by Evolved Artificial Neural Networks. Understanding the structure and function of these neurocon-trollers is important both from an engineering perspective and from the standpoint of the theory of Neural Networks. Here, we introduce a novel algorithm, termed PPA (Performance Prediction Algorithm), that quantitatively measures the contributions of elements of a neural system to the tasks it performs. The algorithm identifies the elements which participate in a behavioral task, given data about performance decrease due to knocking out (lesioning) sets of elements. It also allows the accurate prediction of performance due to multi-element lesions. The effectiveness of the new algorithm is demonstrated in two recurrent neural networks with complex interactions among the elements. The generality and scalability of this method make it an important tool for the study and analysis of evolved neurocontrollers.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
R. Aharonov-Barki, T. Beker, and E. Ruppin. Emergence of memory-driven command neurons in evolved artificial agents. Neural Computation, 13(3), 2001.
R. Barlow, D. Bartholemew, J. Bremner, and H. Brunk. Statistical Inference Under Order Restrictions. John Wiley, New York, 1972.
Dario Floreano and Francesco Mondada. Evolution of homing navigation in a real mobile robot. IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26(3):396–407, June 1996.
Dario Floreano and Francesco Mondada. Evolutionary neurocontrollers for autonomous mobile robots. Neural Networks, 11(7-8):1461–1478, October–November 1998.
Faustino Gomez and Risto Miikkulainen. Incremental evolution of complex general behavior. Adaptive Behavior, 5(3/4):317–342, 1997.
G. D. Knott. Interpolating cubic splines. In National Science Foundation J. C. Cherniavsky, editor, Progress in Computer Science and Applied Logic. Birkhauser, 2000.
Jérôme Kodjabachian and Jean-Arcady Meyer. Evolution and development of neural controllers for locomotion, gradient-following and obstacle-avoidance in artificial insects. IEEE Transactions on Neural Networks, 9(5):796–812, September 1998.
K. S. Lashley. Brain Mechanisms in Intelligence. University of Chicago Press, Chicago, 1929.
Christian Scheier, Rolf Pfeifer, and Yasuo Kunyioshi. Embedded neural networks: Exploiting constraints. Neural Networks, (7-8):1551–1569, October–November 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aharonov, R., Meilijson, I., Ruppin, E. (2001). Understanding the Agent’s Brain: A Quantitative Approach. In: Kelemen, J., Sosík, P. (eds) Advances in Artificial Life. ECAL 2001. Lecture Notes in Computer Science(), vol 2159. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44811-X_23
Download citation
DOI: https://doi.org/10.1007/3-540-44811-X_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42567-0
Online ISBN: 978-3-540-44811-2
eBook Packages: Springer Book Archive