Neural uncertainty and sensorimotor robustness

Authors:
Jose A. Fernandez-Leon;Ezequiel A. Di Paolo
Affiliations:
Centre for Computational Neuroscience and Robotics, Department of Informatics, University of Sussex, Brighton, UK;Centre for Computational Neuroscience and Robotics, Department of Informatics, University of Sussex, Brighton, UK
Venue:
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Year:
2007

Citing 6
Cited 1

Intelligence as adaptive behavior: an experiment in computational neuroethology

Intelligence as adaptive behavior: an experiment in computational neuroethology
On the dynamics of small continuous-time recurrent neural networks

Adaptive Behavior - Special issue on computational neuroethology
Evolutionary robotics and the radical envelope-of-noise hypothesis

Adaptive Behavior
Evolutionary Robotics: The Biology,Intelligence,and Technology

Evolutionary Robotics: The Biology,Intelligence,and Technology
Center-crossing recurrent neural networks for the evolution of rhythmic behavior

Neural Computation
Noise and the Pursuit of Complexity: A Study in Evolutionary Robotics

Proceedings of the First European Workshop on Evolutionary Robotics

Neural Noise Induces the Evolution of Robust Behaviour by Avoiding Non-functional Bifurcations

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats

Quantified Score

Hi-index	0.00

Visualization

Abstract

Real organisms live in a world full of uncertain situations and have evolved cognitive mechanisms to cope with problems based on actions and perceptions which are not always reliable. One aspect could be related with the following questions: could neural uncertainty be beneficial from an evolutionary robotics perspective? Is uncertainty a possible mechanism for obtaining more robust artificial systems? Using the minimal cognition approach, we show that moderate levels of uncertainty in the dynamics of continuous-time recurrent networks correlates positively with behavioral robustness of the system. This correlation is possible through internal neural changes depending on the uncertainty level. We also find that controllers evolved with moderate neural uncertainty remain robust to disruptions even when uncertainty is removed during tests, suggesting that uncertainty helps evolution find regions of higher robustness in parameter space.