Filters








31 Hits in 3.4 sec

Effective and efficient forgetting of learned knowledge in Soar's working and procedural memories

Nate Derbinsky, John E. Laird
2013 Cognitive Systems Research  
We apply this model to the working and procedural memories of Soar.  ...  Effective management of learned knowledge is a challenge when modeling human-level behavior within complex, temporally extended tasks.  ...  Acknowledgment We acknowledge the funding support of the Air Force Office of Scientific Research, contract FA2386-10-1-4127.  ... 
doi:10.1016/j.cogsys.2012.12.003 fatcat:nmtyvdjoqbepphqdf6pz665a3a

An Analysis and Comparison of ACT-R and Soar [article]

John E. Laird
2022 arXiv   pre-print
, memory retrievals, and learning.  ...  It focuses on working memory, procedural memory, and long-term declarative memory. I emphasize the commonalities, which are many, but also highlight the differences.  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Department of Defense  ... 
arXiv:2201.09305v1 fatcat:ro7usqa3rrawphgq7ogdxaekey

Long-term symbolic learning

William G. Kennedy, J. Gregory Trafton
2007 Cognitive Systems Research  
First, in both systems, symbolic learning eventually stopped. Second, learned knowledge was used differently in different stages but the resulting production knowledge was used uniformly.  ...  We investigated the characteristics of long-term, symbolic learning using the Soar and ACT-R cognitive architectures running cognitive models of two simple tasks.  ...  This work was partially supported by the Office of Naval Reactors under job order numbers 55-8551-06, 55-9019-06, and 55-9017-06.  ... 
doi:10.1016/j.cogsys.2007.06.005 fatcat:omrqstwafnf2zim36rncz7rfdm

How Soar Agent Learns: Episodic Memory

Nitin Bansal, S. Srinivasan
2019 International Journal of Computer Applications  
In this paper episodes (previous experiences) which are in the form of WME (working memory elements) work to improve the intelligence.  ...  Learning is performed with the help of episodic memory which store the previous experiences in the form of episodes in order to solve the problem.  ...  Episodic memory in the Soar cognitive architecture must efficiently encode, store, search and reconstruct episodes as snapshots of short term working memory All decisions are made through the combination  ... 
doi:10.5120/ijca2019918328 fatcat:g6voao3uavcq5de5hdubpc6fui

Cognitive Architecture In Mobile Music Interactions

Nate Derbinsky, Georg Essl
2011 Zenodo  
We alsoinclude details of the computational performance of theseagents, evincing that the architecture can support real-timeinteractivity on modern commodity hardware.  ...  This paper explores how a general cognitive architecture canpragmatically facilitate the development and exploration ofinteractive music interfaces on a mobile platform.  ...  In contrast to prior work that applied specialized machine learning algorithms, we use a cognitive architecture, a system that efficiently and generally integrates multiple learning and memory modules  ... 
doi:10.5281/zenodo.1177993 fatcat:sxckbrkqjfeflao5dvbdqm6sti

Architectural Explorations for Modeling Procedural Skill Decay

Ronald Chong
2004 International Conference on Cognitive Modelling  
To better understand skill decay and to test theories and systems aimed at minimizing its effects, it is useful to create computational models capable of exhibiting its main effects.  ...  It also discusses implementation issues with a focus on psychologicallyplausible approaches and explanations of skill decay effects.  ...  Acknowledgements This work was supported by ONR Grant N000140210039.  ... 
dblp:conf/iccm/Chong04 fatcat:b6aoj4u2qnbxjf4nnllo5pqlqi

The problem of expensive chunks and its solution by restricting expressiveness

Milind Tambe, Allen Newell, Paul S. Rosenbloom
1990 Machine Learning  
Chunking creates new items of information, called chunks, based on the results of problem-solving and stores them in the knowledge base.  ...  Soar is an architecture for a system that is intended to be capable of general intelligence. Chunking, a simple experience-based learning mechanism, is Soar's only learning mechanism.  ...  Acknowledgments We thank John Laird, Steve Minton, David Steier, Don Cohen, Bob MacGregor, and mem-bers of the Soar group for many interesting discussions on expensive chunks.  ... 
doi:10.1007/bf00117107 fatcat:6kbbmuavxjdsxc3kdv4ekh6g4i

Comprehensive Working Memory Activation in Soar

John E. Laird, Andrew Nuxoll
2004 International Conference on Cognitive Modelling  
In this paper, we present a comprehensive implementation of working memory activation in Soar that takes advantage of the unique characteristic of Soar's working memory structure, namely persistence.  ...  We demonstrate our model in terms of how it aids the selection of features relevant to learning.  ...  Like most other architectures of this type, Soar has two types of knowledge: working memory (short term, declarative) and production rules (long-term, procedural).  ... 
dblp:conf/iccm/LairdN04 fatcat:ogfqlxdwive3rpxwwvhuns7oku

Enhancing intelligent agents with episodic memory

Andrew M. Nuxoll, John E. Laird
2012 Cognitive Systems Research  
Soar represents procedural knowledge as production rules. Like most other architectures of this type, Soar has two types of knowledge: working memory and procedural memory.  ...  Procedural Memory Procedural memory (or production memory) is a long term memory that consists of a set of production rules that encapsulate the agent's knowledge about how to act in its environment.  ...  The act of retrieving a memory in the current situation can alter the original memory to include features of the current situation. In effect, episodes can leak over into each other over time.  ... 
doi:10.1016/j.cogsys.2011.10.002 fatcat:qsbxe4hi7vcb5lffnxakj3nwcy

A systematic methodology for cognitive modelling

R. Cooper, J. Fox, J. Farringdon, T. Shallice
1996 Artificial Intelligence  
We demonstrate this by reporting three computational experiments involving modifications to the functioning of working memory within Soar.  ...  Although our focus is on Soar, the thrust of the work is more concerned with general methodological issues in cognitive modelling.  ...  In effect Soar can become sidetracked, or forget some information, but later recover.  ... 
doi:10.1016/0004-3702(95)00112-3 fatcat:h6bmtra4uzf3lgoqsalqbk7dpm

New Requirements for Modelling How Humans Succeed and Fail in Complex Traffic Scenarios [chapter]

Andreas Lüdtke
2010 Lecture Notes in Computer Science  
In this text aspects of human decision making in complex traffic environments are described and requirements for cognitive models that shall be used as virtual test pilots or test drivers for new assistance  ...  An extension of the typical cognitive cycle prevalent in extant models is suggested.  ...  The original version of this chapter was revised: The copyright line was incorrect.This has been corrected. The Erratum to this chapter is available at DOI:  ... 
doi:10.1007/978-3-642-11750-3_1 fatcat:fcei5uupejgepmk4ru2joluc6u

Theory and Practice From Cognitive Science [chapter]

Michael Wilson
2000 User Interfaces for All  
This Chapter discusses the cognitive science approach to HCI, and in particular how some cognitive science models can be used to facilitate the goal of User Interfaces for All.  ...  Finally, recent developments in computing technology and cognitive science are outlined, which could work synergistically to create future computer interfaces that are suitable for the broadest possible  ...  Acknowledgments The research reported in this paper was partly funded by CEC Esprit IV grant 20597 to the CHAMELEON project, partly by CEC HCM grant CHRX-CT93-0085 to the ERCIM  ... 
doi:10.1201/9780429285059-8 fatcat:ukhop5vlrnf5np2ehzjqutjstu

A Canonical Theory of Dynamic Decision-Making

John Fox, Richard P. Cooper, David W. Glasspool
2013 Frontiers in Psychology  
The canons cover the whole decision cycle, from the framing of a decision based on the goals, beliefs, and background knowledge of the decision-maker to the formulation of decision options, establishing  ...  However the conceptualization of what decision-making is and methods for studying it vary greatly and this has resulted in fragmentation of the field.  ...  and add, delete or replace information in the working memory.  ... 
doi:10.3389/fpsyg.2013.00150 pmid:23565100 pmcid:PMC3613596 fatcat:pxt4ownzhjaqfnqwub24lmkofa

Rule acquisition events in the discovery of problem-solving strategies

K VANLEHN
1991 Cognitive Science  
In an early report on this work(VanLehn, 1989b), I followed Schoenfeld et al. (in press) in using the term "learning event" to refer to changes in the subject's procedural knowledge.  ...  The only way to augment Soar's long term memory is via an impasse.  ...  Appendix This appendix presents the protocol analyzed in this paper, which is take from Anzai and Simon (1979) .  ... 
doi:10.1016/0364-0213(91)80012-t fatcat:dkjqplqzlvaeli7yg33xeadac4

Rule acquisition events in the discovery of problem-solving strategies

Kurt VanLehn
1991 Cognitive Science  
In an early report on this work(VanLehn, 1989b), I followed Schoenfeld et al. (in press) in using the term "learning event" to refer to changes in the subject's procedural knowledge.  ...  The only way to augment Soar's long term memory is via an impasse.  ...  Appendix This appendix presents the protocol analyzed in this paper, which is take from Anzai and Simon (1979) .  ... 
doi:10.1207/s15516709cog1501_1 fatcat:oswdlmjfwzbono3zyyhngdlcbi
« Previous Showing results 1 — 15 out of 31 results