Teaching an Agent by Playing a Multimodal Memory Game: Challenges for Machine Learners and Human Teachers

As agents become ubiquitous in virtual as well as physical worlds, the importance of learning from real-life human interaction is increasing. Here we explore new learning and teaching strategies for an agent situated in a digital cinema environment to solve a language-vision translation problem by playing a multimodal memory game with humans. We discuss the challenges for machine learners, i.e. learning architectures and algorithms, required to deal with this kind of long-lasting, dynamic scenario. We also discuss the challenges for human teachers to address the new machine learning issues. Based on our preliminary experimental results using the hypernetwork learning architecture we argue for self-teaching cognitive agents that actively interact with humans to generate queries and examples to evaluate and teach themselves.

[1]  R. Gibbs.  Embodiment and Cognitive Science: Concepts , 2005 .

[2]  Earl Hunt,et al.  Individual Differences in the Verification of Sentence-Picture Relationships , 1978 .

[3]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  Donald A. Norman,et al.  Accretion, tuning and restructuring: Three modes of learning , 1976 .

[5]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[6]  Pat Langley,et al.  Cognitive Architectures and General Intelligent Systems , 2006, AI Mag..

[7]  Hubert D. Zimmer,et al.  Levels of binding: types, mechanisms, and functions of binding in remembering , 2006, Handbook of Binding and Memory.

[8]  Raymond J. Mooney,et al.  Learning to sportscast: a test of grounded language acquisition , 2008, ICML '08.

[9]  Byoung-Tak Zhang,et al.  Cognitive learning and the multimodal memory game: Toward human-level machine learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[10]  Luis von Ahn.  Games with a Purpose , 2006, Computer.

[11]  Byoung-Tak Zhang,et al.  Hypernetworks: A Molecular Evolutionary Architecture for Cognitive Learning and Memory , 2008, IEEE Computational Intelligence Magazine.

[12]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[13]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[14]  Alex Kosorukoff,et al.  Human based genetic algorithm , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[15]  Andrea Lockerd Thomaz,et al.  Teachable robots: Understanding human teaching behavior to build more effective robot learners , 2008, Artif. Intell..

[16]  R. Sternberg,et al.  Cognition and intelligence : identifying the mechanisms of the mind , 2004 .

[17]  R. Klatzky,et al.  Semantic factors in cognition , 1978 .

[19]  Manuela M. Veloso,et al.  Teaching multi-robot coordination using demonstration of communication and state sharing , 2008, AAMAS.

[20]  C A Nelson,et al.  Learning to Learn , 2017, Encyclopedia of Machine Learning and Data Mining.

[21]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[22]  S. Grillner,et al.  Microcircuits : the interface between neurons and global brain function , 2006 .

[23]  Yadin Dudai,et al.  Science of memory: concepts , 2007 .

[24]  R. O’Reilly.  Biologically Based Computational Models of High-Level Cognition , 2006, Science.

[25]  Byoung-Tak Zhang,et al.  DNA Hypernetworks for Information Storage and Retrieval , 2006, DNA.