Perceptual learning and abstraction in machine learning: an application to autonomous robotics

This paper deals with the possible benefits of perceptual learning in artificial intelligence. On the one hand, perceptual learning is more and more studied in neurobiology and is now considered as an essential part of any living system. In fact, perceptual learning and cognitive learning are both necessary for learning and often depend on each other. On the other hand, many works in machine learning are concerned with "abstraction" in order to reduce the amount of complexity related to some learning tasks. In the abstraction framework, perceptual learning can be seen as a specific process that learns how to transform the data before the traditional learning task itself takes place. In this paper, we argue that biologically inspired perceptual learning mechanisms could be used to build efficient low-level abstraction operators that deal with real-world data. To illustrate this, we present an application where perceptual-learning-inspired metaoperators are used to perform an abstraction on an autonomous robot visual perception. The goal of this work is to enable the robot to learn how to identify objects it encounters in its environment.

[1]  Yann Chevaleyre,et al.  A meta-learning approach to ground symbols from visual percepts , 2003, Robotics Auton. Syst..

[2]  Lorenza Saitta,et al.  Phase Transitions in Relational Learning , 2000, Machine Learning.

[3]  Fausto Giunchiglia,et al.  Using Abstrips Abstractions -- Where do We Stand? , 1999, Artificial Intelligence Review.

[4]  Ryszard S. Michalski,et al.  Hypothesis-Driven Constructive Induction in AQ17-HCI: A Method and Experiments , 1994, Machine Learning.

[5]  Ron Kohavi,et al.  Feature Subset Selection Using the Wrapper Method: Overfitting and Dynamic Search Space Topology , 1995, KDD.

[6]  Earl D. Sacerdott.  Planning in a hierarchy of abstraction spaces , 1973, IJCAI 1973.

[7]  Ron Kohavi,et al.  The Wrapper Approach , 1998 .

[8]  Alexis Drogoul,et al.  Pixel-based Behavior Learning , 2002, ECAI.

[9]  D. Scott.  Perceptual learning. , 1974, Queen's nursing journal.

[10]  Toby Walsh,et al.  The TSP Phase Transition , 1996, Artif. Intell..

[11]  Refractor.  Vision , 2000, The Lancet.

[12]  Shimon Edelman,et al.  Models of Perceptual Learning in Vernier Hyperacuity , 1993, Neural Computation.

[13]  Jean-Daniel Zucker,et al.  Semantic Abstraction for Concept Representation and Learning , 2001 .

[14]  Jean-Daniel Zucker,et al.  A model of abstraction in visual perception , 2001, Appl. Artif. Intell..

[15]  H. Bülthoff,et al.  Learning to recognize objects , 1999, Trends in Cognitive Sciences.

[16]  Vicki Bruce,et al.  Learning new faces , 2002 .

[17]  Stevan Harnad.  The Symbol Grounding Problem , 1999, ArXiv.

[18]  Toby Walsh,et al.  Phase Transitions from Real Computational Problems , 1995 .

[19]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[20]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[21]  Michael H. Herzog,et al.  Top-down information and models of learning , 2002 .

[22]  Eric B. Baum,et al.  A Proposal for More Powerful Learning Algorithms , 1989, Neural Computation.

[23]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[24]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[25]  Saul Amarel,et al.  On representations of problems of reasoning about actions , 1968 .

[26]  Yann Chevaleyre,et al.  A Framework for Learning Rules from Multiple Instance Data , 2001, ECML.

[27]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .

[28]  P. Pandurang Nayak,et al.  A Semantic Theory of Abstractions , 1995, IJCAI.