Perceptual learning and abstraction in machine learning

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 depends 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 mechanism could be used to build efficient low-level abstraction operators that deal with real world data.

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

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

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

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

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

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

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

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

[9]  Alexis Drogoul,et al.  Robots as a Social Species: the MICRobES Project , 2000 .

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

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

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

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

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

[15]  Jean-Gabriel Ganascia,et al.  Representation Changes for Efficient Learning in Structural Domains , 1996, ICML.

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

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

[18]  P. Langley.  Selection of Relevant Features in Machine Learning , 1994 .

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

[20]  Yann Chevaleyre,et al.  Learning Rules from Multiple Instance Data: Issues and Algorithms , 2001 .

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

[22]  Franc Solina,et al.  Learning to recognize the object's shape , 1995 .

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

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

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

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

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

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

[29]  Alexis Drogoul,et al.  The MICRobES Project, an Experimental Approach towards "Open Collective Robotics" , 2000, DARS.

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

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