Learning to Attend -- From Bottom-Up to Top-Down

Authors:
Hector Jasso;Jochen Triesch
Affiliations:
Dept. of Computer Science and Engineering, University of California, San Diego, La Jolla, CA 92093, USA;Frankfurt Institute for Advanced Studies, J.W. Goethe University, Frankfurt am Main, Germany and Dept. of Cognitive Science, University of California, San Diego, La Jolla, CA 92093, USA
Venue:
Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
Year:
2008

Citing 6
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Combining Embodied Models and Empirical Research for Understanding the Development of Shared Attention

ICDL '02 Proceedings of the 2nd International Conference on Development and Learning
2006 Special issue: A probabilistic model of gaze imitation and shared attention

Neural Networks - 2006 Special issue: The brain mechanisms of imitation learning
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Emergence of Mirror Neurons in a Model of Gaze Following

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
The cog project: building a humanoid robot

Computation for metaphors, analogy, and agents

Quantified Score

Hi-index	0.00

Visualization

Abstract

The control of overt visual attention relies on an interplay of bottom-up and top-down mechanisms. Purely bottom-up models may provide a reasonable account of the looking behaviors of young infants, but they cannot accurately account for attention orienting of adults in many natural behaviors. But how do humans learn to incorporate top-down mechanisms into their control of attention? The phenomenon of gaze following, i.e. the ability to infer where someone else is looking and to orient to the same location, offers an interesting window into this question. We review findings on the emergence of gaze following in human infants and present a computational model of the underlying learning processes. The model exhibits a gradual incorporation of top-down cues in the infant's attention control. It explains this process in terms of generic reinforcement learning mechanisms. We conclude that reinforcement learning may be a major driving force behind the incorporation of top-down cues into the control of visual attention.