57,881 Hits in 5.5 sec

Integrating representation learning and skill learning in a human-like intelligent agent

Nan Li, Noboru Matsuda, William W. Cohen, Kenneth R. Koedinger
2015 Artificial Intelligence  
SimStudent: An intelligent pedagogical agent that helps students learn and researchers learn how students learn (2014).  ...  Learning to solve algebraic equations by teaching a computer agent. In M. F. Pinto & T. F.  ...  AWARDS AND CERTIFICATES  ... 
doi:10.1016/j.artint.2014.11.002 fatcat:4z3qb7e7sbadpf3wd6w3lwyuhy

Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human-like learning

Pierre-Yves Oudeyer
2017 Behavioral and Brain Sciences  
Autonomous lifelong development and learning are fundamental capabilities of humans, differentiating them from current deep learning systems.  ...  These mechanisms guide exploration and autonomous choice of goals, and integrating them with deep learning opens stimulating perspectives.  ...  Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human-like learning doi:10.1017/S0140525X17000243, e275 Pierre-Yves Oudeyer Inria and Ensta Paris-Tech  ... 
doi:10.1017/s0140525x17000243 pmid:29342696 fatcat:lgzpqnpl4rheteun7cquan7f44

Integrating Perceptual Learning with External World Knowledge in a Simulated Student [chapter]

Nan Li, Yuandong Tian, William W. Cohen, Kenneth R. Koedinger
2013 Lecture Notes in Computer Science  
Here we explore the generality of these methods by considering a very different task, article selection in English, where little problem-solving is done, but where complex prior perceptual skills and large  ...  Experimental results show that the extended Sim-Student successfully learns the tutored article selection grammar rules, and can be used to discover a student model that predicts human student behavior  ...  Acknowledgements We thank Ruth Wylie for helpful discussion, and the National Science Foundation (#SBE-0354420) for funding of the Pittsburgh Science of Learning Center.  ... 
doi:10.1007/978-3-642-39112-5_41 fatcat:wtlyp3hq3zdlxf6hgtgla3nrk4

Special corner on "cognitive robotics"

Stefan Kopp, Jochen J. Steil
2011 Cognitive Processing  
Acknowledgments We thank all authors for sharing their exciting and important ideas and work.  ...  We are also very grateful to the reviewers that helped to select these papers and provided valuable comments to their authors (  ...  In this sense, cognitive robots embody the behavior of intelligent ''Cartesian agents'' in the physical world (or a virtual world, in the case of simulated CR).  ... 
doi:10.1007/s10339-011-0415-y pmid:21953385 fatcat:kq7uax4xgbbpvaupcn5twt5tmi

Cognitive Architectures and General Intelligent Systems

Pat Langley
2006 The AI Magazine  
Subfields like knowledge representation and machine learning focus on idealized tasks like inheritance, classification, and reactive control that ignore the richness and complexity of human intelligence  ...  I illustrate these ideas using a particular architecture-ICARUS-by examining its claims about memories, about the representation and organization of knowledge, and about the performance and learning mechanisms  ...  Dongkyu Choi, Seth Rogers, and Daniel Shapiro have played central roles in the design and implementation of ICARUS, with the former developing the driving agent I have used as my central example.  ... 
doi:10.1609/aimag.v27i2.1878 dblp:journals/aim/Langley06 fatcat:4voh7ltm7vbsnd5wvz6xpnzbq4

Embodied Artificial Intelligence through Distributed Adaptive Control: An Integrated Framework [article]

Clément Moulin-Frier, Jordi-Ysard Puigbò, Xerxes D. Arsiwalla, Martì Sanchez-Fibla, Paul F. M. J. Verschure
2017 arXiv   pre-print
Regarding integration, we note that the most impactful recent contributions have been made possible through the integration of recent Machine Learning methods (based in particular on Deep Learning and  ...  In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field.  ...  This is, however, not a sufficient condition for an agent to continuously learn increasingly complex skills.  ... 
arXiv:1704.01407v3 fatcat:jqdvpkzjrnedzpxfz7bxhfn5mm

Improvising in Creative Symbolic Interaction [chapter]

Gérard Assayag
2016 Lecture Notes Series, Institute for Mathematical Sciences, National University of Singapore  
Creative Symbolic Interaction brings together the advantages from the worlds of interactive real-time computing and intelligent, content-level analysis and processing, in order to enhance and humanize  ...  mathematical symbolic structures and cognitively inspired dynamical processes belongs to a general scheme that is likely to grow in many artistic and non-artistic domains.  ...  Improvised Machine Musicianship projects described in this document partly funded by Agence nationale de la recherche (ANR) projects ImproTech, SOR2 (finished) and DYCI2 (starting).  ... 
doi:10.1142/9789813140103_0004 fatcat:zz2avfpjxbapfakzpkesy54pga

Creative Symbolic Interaction

Gérard Assayag
2014 Proceedings of the SMC Conferences  
Improvised Machine Musicianship projects described in this document partly funded by Agence nationale de la recherche (ANR) projects ImproTech, SOR2 (finished) and DYCI2 (starting).  ...  Integrating listening and learning in the very process of artistic interaction makes it possible to program software agents with the skills to react in real-time to human performance in man-machine improvisation  ...  This human-agent interaction will be in effect extended to complex configuration involving potentially a great number of agents -human and artificial -learning and evolving from each other.  ... 
doi:10.5281/zenodo.850441 fatcat:arpsr4vnd5ddhmha4vcyw4e2v4

Modularity and Specialized Learning in the Organization of Behaviour [chapter]

Joanna Bryson, Lynn Andrea Stein
2001 Perspectives in Neural Computing  
Research in artificial neural networks (ANN) has provided new insights for psychologists, particularly in the areas of memory, perception, representation and learning.  ...  We propose that in the mean time, psychologists may want to consider modelling learning in specialised hybrid systems which can support both complex behaviour and neural learning.  ...  Acknowledgements Thanks to David Glasspool for his comments and suggestions.  ... 
doi:10.1007/978-1-4471-0281-6_6 dblp:conf/ncpw/BrysonS00 fatcat:5m4uw4jvyzeu3anvln5twfwxxe

A Pedagogical Agent as an Interface of an Intelligent Tutoring System to Assist Collaborative Learning

Ana Lilia Laureano-Cruces, Enrique Acuña-Garduño, Lourdes Sánchez-Guerrero, Javier Ramírez-Rodríguez, Martha Mora-Torres, Blanca R. Silva-López
2014 Creative Education  
The concept of the intelligent tutoring system, conceived as a pedagogical interface agent (interface with human features that permits interaction between system and user), forms the basis of this study  ...  This is achieved by dynamic interaction on a system that has a collaborative and distributed interaction facility, in which the agent is conceived as an educational tool.  ...  It is also part of the Divisional Soft Computing and Applications project of the Intelligent E-Learning course funded by the same university.  ... 
doi:10.4236/ce.2014.58073 fatcat:5bhe3a3jqnhqxaan3pgoo46r7a

Integration-Kid: A Learning Companion System

Tak-Wai Chan
1991 International Joint Conference on Artificial Intelligence  
This paper describes a learning companion system called Integration-Kid in the domain of learning indefinite integration. A learning companion system is an intelligent tutoring system of a new breed.  ...  Apart from the teacher, a learning companion models after an additional agent, called the learning companion. The learning companion acts as a companion for the human student in learning.  ...  Acknowledgements I would like to thank Arthur Baskin, Richard Dennis, Howard Aizenstein, and Lisa Chiu for their support during various stages of this research.  ... 
dblp:conf/ijcai/Chan91 fatcat:ck2jzrdknzca5guna4uar7bhp4

Intelligent problem-solving as integrated hierarchical reinforcement learning

Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D. H. Nguyen, Martin V. Butz, Stefan Wermter
2022 Nature Machine Intelligence  
Hierarchical reinforcement learning is a promising computational approach that may eventually yield comparable problem-solving behaviour in artificial agents and robots.  ...  Here, we propose steps to integrate biologically inspired hierarchical mechanisms to enable advanced problem-solving skills in artificial agents.  ...  Acknowledgements The authors acknowledge funding by the DFG (projects IDEAS, LeCAREbot, TRR169, SPP 2134, RTG 1808, EXC 2064/1) and the Humboldt Foundation and Max Planck Research School IMPRS-IS.  ... 
doi:10.1038/s42256-021-00433-9 fatcat:5rwjbkbqhve53l2dsgr3fuj3aa

Social Neuro AI: Social Interaction as the "Dark Matter" of AI

Samuele Bolotta, Guillaume Dumas
2022 Frontiers in Computer Science  
We argue that the complex human cognitive architecture owes a large portion of its expressive power to its ability to engage in social and cultural learning.  ...  In the first section, we discuss how social learning plays a key role in the development of intelligence.  ...  THE IMPORTANCE OF SOCIAL LEARNING Social Learning Categories Various approaches have been proposed in order to reach a human-like level of intelligence.  ... 
doi:10.3389/fcomp.2022.846440 fatcat:chmdlrbdivbjzbobrrf7r4swza

Vygotskian Autotelic Artificial Intelligence: Language and Culture Internalization for Human-Like AI [article]

Cédric Colas, Tristan Karch, Clément Moulin-Frier, Pierre-Yves Oudeyer
2022 arXiv   pre-print
We focus on language especially, and how its structure and content may support the development of new cognitive functions in artificial agents, just like it does in humans.  ...  To that end, a promising developmental approach recommends the design of intrinsically motivated agents that learn new skills by generating and pursuing their own goals - autotelic agents.  ...  For an embodied and situated rl agent, learning a skill (e.g. playing chess) is about learning to act so as to maximize future rewards measuring progression in that skill (e.g. +1 for winning a game, -  ... 
arXiv:2206.01134v1 fatcat:nr7m5nsbijhmphfe6uuxxrosca

Towards Developmental AI: The paradox of Ravenous Intelligent Agents

Michelangelo Diligenti, Marco Gori, Marco Maggini
2011 International Workshop on Neural-Symbolic Learning and Reasoning  
Introduction In spite of extraordinary achievements in specific tasks, nowadays intelligent agents are still striving for acquiring a truly ability to deal with many challenging human cognitive processes  ...  A unified approach to embrace the behavior of intelligent agents involved in both perceptual and symbolic information is based on expressing learning data and explicit knowledge by constraints [Diligenti  ... 
dblp:conf/nesy/DiligentiGM11 fatcat:mbwdwty6qnhc3gzji3ar2u4wge
« Previous Showing results 1 — 15 out of 57,881 results