Home



Ron Sun, Ph.D.  

Professor
Cognitive Science Department 
Rensselaer Polytechnic Institute
110 Eighth Street, Carnegie 302A
Troy, New York 12180, USA

Email: rsun [at] rpi [dot] edu
Web: the RPI homepage   
Web: the HASS faculty page
Web: the CogArch Lab page
Web: the Google Scholar page 
  
 

INDEX


RESEARCH INTERESTS


My research interest lies in the study and modeling of cognitive agents, especially in their abilities to learn, reason, and act in the real world. More specifically, my research can be roughly categorized into the following main strands: (1) cognitive architectures, (2) connectionist and hybrid models, as well as (3) multi-agent interaction, cognitive social simulation, and cognitive social sciences.

Cognitive Architectures

The goal of the work on cognitive architecture is two fold: to better understand human cognition (broadly defined) in various domains and to develop more unified models (cognitive architectures) for better capturing human cognition generally. Such work thus includes both psychological experiments and computational modeling and simulation. 

A hybrid cognitive architecture Clarion has been continuously developed over the past three decades, which combines both implicit and explicit processes and both procedural and declarative processes in one unified framework. See Clarion

In particular, this cognitive architecture addresses the motivation-cognition-environment interaction, instead of focusing only on cognition in the narrow sense. For instance, it addresses the motivation-cognition interaction, in order to account for the relationship between motivation and performance. It also incorporates emotion, personality, morality, and so on, on the basis of motivation. The model is being used to capture, explain, and simulate a wide variety of relevant human data and phenomena.

This cognitive architecture also addresses the interaction of implicit and explicit cognition. Implicit processes have been shown to have tremendous impact on human cognition and yet they have not been taken seriously into consideration in most cognitive models. Clarion addresses not only implicit processes along side of explicit processes, but, more importantly, also their interaction in learning, reasoning, and various other activities. The resulting model is parsimonious in structure and possesses a variety of learning, reasoning, and other capabilities.

Learning in this cognitive architecture has been particularly concerned with skill acquisition in various domains, ranging from highly intellectual to sensory-motor tasks. It is accomplished, in the main, by reinforcement learning supplemented with rule induction.  The model performs autonomous learning. It develops different types of representations, symbolic and subsymbolic, along side each other. The model has been used to capture, explain, and simulate a wide variety of human skill learning phenomena. See learning.

One of the technical focuses in this regard was the extraction of explicit plans (open-loop policies) based on the results of reinforcement learning, to enable explicit reasoning of plans, without a priori domain knowledge to begin with. A variety of algorithms have been explored for such plan extraction.

Another technical focus was the development of modular reinforcement learning models, in which multiple modules (or agents) compete and cooperate with each other to accomplish tasks, without a priori division of the tasks (i.e., without using any a priori domain-specific knowledge). See multi-agent learning.

Connectionist Reasoning, Knowledge Representation, and Hybrid Models

Early on, the research work was mainly concerned with everyday commonsense reasoning by agents. This type of reasoning was characterized by a mixture of rule-based and similarity-based processes, exhibiting both rigor and flexibility. To capture such reasoning, a hybrid connectionist architecture (named CONSYDERR) was developed with both localist and distributed components, that unified rule-based and similarity-based processes and accounted for a variety of CSR patterns. See reasoning.

Within the framework, the following issues were also investigated: (1) The connectionist implementations of rules, logics, and schemas, and the variable binding problem in such implementations. They formed the basis for complex reasoning in connectionist models. (2) Inheritance reasoning, which is an integral part of many CSR patterns. An intensional approach was developed within CONSYDERR that works in constant time. This work suggests that other similar reasoning patterns may also be handled intensionally. (3) Causality, which is an important commonsense construct. A connectionist account was developed based on CONSYDERR, which extended the existing logic-based account and dealt better with the inexact, cumulative, and subjective nature of commonsense causal reasoning. (4) Some attempts have also been made to extend the framework to deal with metaphor and analogy. 

The interest in hybrid models also lies in developing more powerful, more integrated models that are capable of autonomous learning, acquiring both symbolic and subsymbolic knowledge and utilizing their synergy to achieve better performance. Psychological models of human learning were explored, especially those concerned with integrated learning of multiple forms of knowledge, as well as machine learning and neural network techniques and theories, especially those concerned with reinforcement learning. A synthesis of these two strands of work led to advances in developing hybrid models providing new insights and impetus. See learning.

Cognitive Social Simulation and Cognitive Social Sciences

Another general area of interest is: multi-agent interaction, cognitive social simulation, and cognitive social sciences. Extending the work on cognitive architectures beyond individual agents, social interaction needs to be taken into consideration. Social simulation on the basis of cognitive architectures (i.e., cognitive social simulation) enabled the exploration and understanding of many social phenomena in relation to individual cognition. See Cognitive Social Simulation.  See also Cognitive Social Sciences.

Biographical Information

See Wikipedia. See also the old bio.


ANNOUNCEMENTS

1. To see a description of the recent books, click on a title:


2. To see a description of the past conferences, workshops, and/or journal special issues he (co)organized, click on a title:

3. To see a brief description of our Ph.D program in Cognitive Science, AI and Neural Nets, click here. If you need application forms for the Ph.D program, click here.

Note that I prefer only to supervise graduate students and post-docs who know a lot about my research (i.e., read some of my papers; see below) and wish to do related work. However, I am willing to consider proposals that are slightly afield from exceptionally outstanding students. 



ONLINE COGNITIVE SCIENCE AND AI RESOURCES

1. SOME JOURNALS (of which Ron Sun serves on the editorial board):

2. HYBRID SYSTEMS RESOURCES:

An introduction to hybrid systems (by Ron Sun, an entry in International Encyclopedia of Social and Behavioral Sciences)

Surveys of hybrid systems: An article by Ron Sun (appeared in: Connectionist-Symbolic Integration. Lawrence Erlbaum Associates. 1997), an article by S. Wermter and R. Sun (appeared in: S. Wermter and R. Sun, eds. Hybrid Neural Systems. Springer-Verlag, Heidelberg. 2000) (PDF)an article by A. Browne and R. Sun (appeared in: Expert Systems, Vol.16, No.3, 189-207. 1999), and another article by A. Browne and R. Sun (appeared in: Neural Networks, 2001).

Hybrid List moderated by Ron Sun

3. COGNITIVE ARCHITECTURES RESOURCES

4. COGNITIVE MODELING RESOURCES at Cognitive Science Society

5. OTHER RESOURCES


SELECTED PUBLICATIONS

Publications by Subject Areas:

Selected Journal Papers: 

  • R. Sun, Full human-machine symbiosis and truly intelligent cognitive systems. AI and Society: Journal of Knowledge, Culture and Communication, in press.
  • R. Sun, Interpreting psychological notions: A dual-process computational theory. Journal of Applied Research in Memory and Cognition, Vol.4, No.3, pp.191–196. 2015.
  • S. Helie and R. Sun, Autonomous learning in psychologically-oriented cognitive architectures: A survey. New Ideas in Psychology. Vol.34, pp.37–55. 2014. 
  • R. Sun, Moral judgment, human motivation, and neural networks. Cognitive Computation, Vol.5, No.4, pp.566-579. 2013. 
  • R. Sun and R. Mathews, Implicit cognition, emotion, and meta-cognitive control. Mind and Society (the special issue on Dual Processes Theories of Language and Thinking), Vol.11, No.1, pp.107-119. 2012.
  • R. Sun, N. Wilson, and R. Mathews, Accounting for certain mental disorders within a comprehensive cognitive architecture. Cognitive Computation, Vol.3, No.2, pp.341-359. 2011.
Books: 
General Overviews: 
Hybrid Reinforcement Learning:
Other Papers on Human Learning:
Other Papers on Multi-Agent Systems and Social Simulation:
Other Papers on Machine Learning:
Other Hybrid Models Papers:
  • N. Wilson and R. Sun, Coping with bullying: A computational emotion-theoretic account. Proceedings of the Annual Conference of Cognitive Science Society, Quebec City, Quebec, Canada. pp.3119-3124. Published by Cognitive Science Society, Austin, Texas.  July, 2014.
  • N. Wilson, R. Sun, and R. Mathews, A motivationally based computational interpretation of social anxiety induced stereotype bias . Proceedings of the Annual Conference of the Cognitive Science Society, pp.1750-1755. Cognitive Science Society, Austin, Texas. 2010.
  • S. Helie and R. Sun, Creative problem solving: A CLARION theory . Proceedings of the 2010 International Joint Conference on Neural Networks, Barcelona, Spain. pp.1460-1466. IEEE Press, Piscataway, NJ. 2010.
  • S. Helie and R. Sun, Simulating incubation effects using the explicit-implicit interaction with Bayes factor (EII-BF) Model . Proceedings of the International Joint Conference on Neural Networks, Atlanta, Georgia, USA. pp.1199-1205. IEEE Press, Piscataway, NJ. 2009.
  • S. Helie and R. Sun, Knowledge integration in creative problem solving. Proceedings of the 2008 Annual Conference of the Cognitive Science Society, Washington, DC. pp.1681 -1686. Published by the Cognitive Science Society. July, 2008.
  • R. Sun and X. Zhang, Accounting for similarity-based reasoning within a cognitive architecture. Proceedings of the 26th Annual Conference of the Cognitive Science Society, Chicago. Lawrence Erlbaum Associates, Mahwah, NJ. 2004.
  • R. Sun and X. Zhang, Accounting for discovery in a cognitive architecture. Proceedings of the 25th Annual Conference of the Cognitive Science Society, Boston, MA. Lawrence Erlbaum Associates, Mahwah, NJ. 2003.
  • R. Sun, Beyond simple rule extraction: the extraction of planning knowledge from reinforcement learners. Proceedings of the International Joint Conference on Neural Networks, Como, Italy. July 24-27, 2000. IEEE Press, Piscataway, NJ.
  • S. Wermter and R. Sun, An overview of hybrid neural systems (PDF) In: S. Wermter and R. Sun, (eds.) Hybrid Neural Systems. Springer-Verlag, Heidelberg. 2000.
  • R. Sun, Introduction to connectionist symbolic integration. In: R. Sun and F. Alexandre, (eds.) Connectionist-Symbolic Integration. Lawrence Erlbaum Associates. 1997.
  • R. Sun and T. Peterson, A hybrid agent architecture for reactive sequential decision making. In: R. Sun and F. Alexandre, (eds.) Connectionist-Symbolic Integration. Lawrence Erlbaum Associates. 1997.
  • R. Sun, Connectionist models of reasoning. In: O. Omidvar and C. Wilson (ed.), Progress in Neural Networks, Vol. 5, Chapter 5. Ablex Publishing, Norwood, NJ. 1997.
  • R. Sun, Hybrid connectionist models. AI Magazine. 17 (2), pp.99-103, Summer 1996.
  • R. Sun, A microfeature-based approach toward metaphor interpretation. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-95). pp.424-430. Morgan Kaufmann, San Francisco, CA. 1995.
  • R. Sun, On neural networks and symbolic processing. In: R. Sun and L. Bookman, (eds.) Computational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic Publishers. 1994.
  • R. Sun, "Variables and logics in connectionist models." in V. Honavar and L. Uhr, (eds.) Artificial Intelligence and Neural Networks: Steps towards Principled Integration, Vol. 1. Academic Press, Reading, MA. 1994.
  • R. Sun, "A two-level architecture for structuring knowledge for commonsense reasoning." Proceedings of the IEEE International Conference on Neural Networks. Orlando, FL. 1994.
  • R. Sun, "The CONSYDERR architecture." Proceedings of the International Conference on Fuzzy Logic, Neural Networks and Soft Computing. pp. 153-155. Iizuka, Japan. 1994
  • R. Sun, "Implementing schemas and logics in connectionist models." Proceedings of the 1st International Symposium on Integrating Knowledge and Neural Heuristics. pp. 32-39. Pensacola Beach, FL. 1994.
  • R. Sun, "A two-level hybrid architecture for commonsense reasoning." In: R. Sun and L. Bookman, (eds.) Computational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic Publishers. 1994.
  • L. Bookman and R. Sun, "Integrating neural and symbolic processes (an editorial)." Connection Science, special issue on integrating neural and symbolic processes, Vol. 5, No. 3-4. 1993.
  • R. Sun, "On neural networks and symbolic processing." Proceedings of the 1st New Zealand International Conference on Neural Networks and Expert Systems. pp 5-7. ACM Press, New York, NY. 1993.
  • R. Sun, "Connectionist models of commonsense reasoning." in D. Levine et al (eds.), Neural Networks for High Level Knowledge Representation and Inference. pp 241-268. Lawrence Erlbaum Associates. Hillsdale, NJ. 1993.
  • R. Sun, "Neural schemas and connectionist logics: a synthesis of the symbolic and the subsymbolic." Proceedings of the Workshop on Schema Theory and Neural Networks." Center for Neural Engineering, Los Angeles. 1993.
  • R. Sun and L. Bookman, "How do symbols and networks fit together?" Artificial Intelligence magazine. pp. 20-23. Summer, 1993.
  • R. Sun, "Fuzzy evidential logic: a model of causality for commonsense reasoning." Proceedings of the 14th Cognitive Science Society Conference, Lawrence Erlbaum Associates. Hillsdale, NJ. pp. 1134-1139. 1992.
  • R. Sun, "An efficient connectionist inheritance scheme." Proceedings of the 2nd Pacific Rim International Conference on Artificial Intelligence, Seoul, Korea. 1992.
  • R. Sun, L. Bookman, and S. Shekhar, (eds.), The Working Notes of the AAAI Workshop on Integrating Neural and Symbolic Processes. American Association for Artificial Intelligence, Menlo Park, CA. 1992.
  • R. Sun and D. Waltz, "A neurally inspired massively parallel model of rule based reasoning." In: B. Soucek (ed.) Neural and Intelligent Systems Integration. John Wiley and Sons, New York, NY. pp. 341-381. 1992.
  • R. Sun, "Connectionist models of rule-based reasoning." Proceedings of the 13th Cognitive Science Conference, Lawrence Erlbaum Associates, Hillsdale, NJ. pp. 437-442. 1991 (received the 1991 David Marr Award in Cognitive Science).
  • R. Sun, "Chunking and connectionism." Neural Network Review, Vol. 4, No. 2. pp. 76-78. 1991.
  • R. Sun, "The discrete neuronal model and the probabilistic discrete neuronal model." In: B. Soucek (ed.) Neural and Intelligent Systems Integration, John Wiley and Sons, New York, NY. pp. 161-178. 1991.
  • R. Sun, "Neural network models of reasoning." Proceedings of International Joint Conference on Neural Networks, Singapore. November 1991.
  • R. Sun, "The discrete neuronal model and the probabilistic discrete neuronal model." Proceedings of International Neural Network Conference (Paris 1990). pp. 902-907. Kluwer, Netherlands. 1990.
  • R. Sun, "A discrete neural network model for conceptual representation and reasoning." Proceedings of the 11th Cognitive Science Society Conference. pp. 916-923. Lawrence Erlbaum Associates, Hillsdale, NJ. 1989.
  •  
Other Topics
  • S. Helie, R. Sun, and L. Xiong, Mixed effects of distractor tasks on incubation. Proceedings of the 2008 Annual Conference of the Cognitive Science Society, Washington, DC. pp.1251-1256. Published by the Cognitive Science Society. July, 2008.
  • R. Sun, X. Zhang, and R. Mathews, Modeling meta-cognition in a cognitive architecture. Proceedings of the 27th Annual Conference of the Cognitive Science Society, Stresa, Italy. Lawrence Erlbaum Associates, Mahwah, NJ. 2005.
  • R. Sun, A microfeature-based approach toward metaphor interpretation. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-95). 1995.
  • R. Sun, Similarity in cognition: a review of similarity and analogical reasoning. Artificial Intelligence Magazine, Vol. 14, No. 4. pp. 81-84. Fall, 1993.
  • R. Sun and D. Waltz, "Neural networks and human intelligence: A review of brain and neural modeling." Journal of Mathematical Psychology, Vol. 34, No. 4. pp. 483-488. 1990.

                                            To download the papers, try also the ftp site.




                                            Click for Albany, NY Forecast Click for Albany, NY Forecast



                                            RPI Cognitive Science Dept Homepage