Abstract
In this work we present the Cognitive Engine, an integrated system whose architectural characteristics and operational capabilities are designed to approximate human visual intelligence. As humans usually do, the Cognitive Engine tries to make sense of a scene by meaningfully clustering visual data: basic individual movements are interpreted as constituting a particular action, and patterns of actions are gathered into more complex activities. In this respect, the Cognitive Engine results from augmenting the ACT-R cognitive architecture – a modular computational system used to model human cognitive processes – with relevant background knowledge embedded in HOMinE, a semantic resource for actions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
“A complex perception cannot be explained by the linear sum of the sensations that its parts arouse” [29], p. 118.
- 2.
- 3.
This was the genesis of using the word ‘ontology’ in AI. Ontology, ‘the study of being as such’ – as Aristotle named it – in fact originated as a philosophical discipline.
- 4.
The adjective ‘hybrid’ is used to emphasize the heterogeneity of resources we are adopting for the purposes of the project. For a general survey on hybrid semantic approaches see [35]. For the sake of readability we will henceforth omit the mid-adjective computational.
- 5.
We refer here to the very broad notion of ‘frame’ introduced by Minsky: “frames are data-structure for representing a stereotyped situation, like being in a certain kind of living room, or going to a child’s birthday party” [30].
- 6.
Henceforth abbreviated with CE.
- 7.
For instance, DOLCE adapts Allen’s temporal axioms [2], which are considered as state of the art in temporal representation and reasoning.
- 8.
- 9.
- 10.
Far from willing to deepen a topic that is out of scope to treat in our contribution, we refer the reader to [15] for details concerning marker–passing algorithms. Note that these inference mechanisms in SCONE are generally consistent with the activation-based retrievals mechanisms in ACT-R, raising an additional level of compatibility between the two frameworks.
- 11.
We will describe in Sect. 8.3.2 how SCONE functions as bridging component between ACT-R cognitive architecture and HOMinE knowledge resource.
- 12.
AKA Unique Beginners [16].
- 13.
01835496 move#1, travel#1, go#1, locomote#1 (change location; move, travel, or proceed) “How fast does your new car go?”; “The soldiers moved towards the city in an attempt to take it before night fell”. 01850315 move#2, displace#4 (cause to move or shift into a new position or place, both in a concrete and in an abstract sense) “Move those boxes into the corner, please”; “The director moved more responsibilities onto his new assistant”.
- 14.
- 15.
These sequences reflect the most likely atomic events (so called ‘micro-actions’, ‘micro-states’ and‘micro-poses’) occurring in the environment, detected and thresholded by machine vision algorithms. The addition symbol exemplifies temporal succession while numbers stand for entity unique identifiers. For the sake of readability, we omit here the temporal information about start and end frames of the single atomic-events, as well as spatial coordinates of the positions of objects.
- 16.
http://www.visint.org/datasets.html The description task applies to the same dataset.
- 17.
The qualitative duration of an interval may vary with the circumstances: accordingly, we are working on adding a mechanism for data-driven context sensitivity to CE.
- 18.
The multiple runs are motivated by the need to reflect the stochasticity of the ACT-R architecture, specifically in information retrieval.
- 19.
To reward the match between machine output and human annotations used for training.
- 20.
Only (ii) and (iii) are mutually exclusive.
References
Albertazzi, L., Van Tonder, L., Vishwanath, D. (eds.): Perception Beyond Inference. The Information Content of Visual Processes. MIT, Cambridge (2010)
Allen, J.F.: An interval based representation of temporal knowledge. In: 7th International Joint Conference on Artificial Intelligence, vol.1, pp. 221–226. IJCAI/Morgan Kaufmann, Vancouver (1983)
Anderson, J.: The Architecture of Cognition. Harvard University Press, Cambridge (1983)
Anderson, J.: How Can the Human Mind Occur in the Physical Universe? Oxford University Press, Oxford/New York (2007)
Anderson, J., Lebiere, C.: The Atomic Components of Thought. Erlbaum, Mahwah (1998)
Anderson, J., Lebiere, C.: The newell test for a theory of cognition. Behav. Brain Sci. 26, 587–637 (2003)
Baader, F., Calvanese, D., Mcguinness, D.L., Nardi, D., Patel-Schneider, P.F. (eds.): The Description Logic Handbook: Theory, Implementation and Applications. Cambridge University Press, Cambridge/New York (2003)
Ball, J., Rodgers, S., Gluck, K.: Integrating act-r and cyc in a large-scale model of language comprehension for use in intelligent systems. In: Papers from the AAAI workshop, pp. 19–25. AAAI, Menlo Park (2004)
Best, B., Gerhart, N., Lebiere, C.: Extracting the ontological structure of cyc in a large-scale model of language comprehension for use in intelligent agents. In: Proceedings of the 17th Conference on Behavioral Representation in Modeling and Simulation (2010). http://www.adcogsys.com/pubs/Brims2010-best-gerhart-lebiere-opencyc.pdf
Biederman, I.: Recognition by components: a theory of human image understanding. Psychol. Rev. 94, 115–147 (1987)
Burchardt, A., Erk, K., Frank, A.: A WordNet detour to FrameNet. In: Schröder, B., Fisseni, B. Schmitz, H.-C., Wagner, P. (eds.) Sprachtechnologie, Mobile Kommunikation und Linguistische Resourcen. Computer Studies in Language and Speech, vol. 8, pp. 408–421. Peter Lang, Frankfurt am Main (2005)
Casati, R., Varzi, A. (eds.): Events. Dartmouth, Aldershots (1996)
Douglas, S., Ball, J., Rodgers, S.: Large declarative memories in ACT-R. In: Proceedings of the 9th International Conference of Cognitive Modeling, Manchester (2009)
Edmond, B.: Wn-lexical: an ACT-R module built from the wordnet lexical database. In: Proceedings of the 7th International Conference of Cognitive Modeling, Trieste, pp. 359–360 (2006)
Fahlman, S.: Using Scone’s multiple-context mechanism to emulate human-like reasoning. In: First International Conference on Knowledge Science, Engineering and Management (KSEM’06). Lecture Notes in Artificial Intelligence. Springer, Guilin (2006)
Fellbaum, C. (ed.): WordNet, an Electronic Lexical Database. MIT, Boston (1998)
Fillmore, C.J.: The case for case. In: Bach, E. Harms, T. (eds.) Universals in Linguistic Theory. Rinehart and Wiston, New York (1968)
Forsyth, D.A., Ponce, J.: Computer Vision, a Modern Approach. Prentice Hall, New Jersey, USA (2004)
Gangemi, A., Guarino, N., Masolo, C., Oltramari, A.: Sweetening WordNet with DOLCE. AI Mag. 3, 13–24 (Fall 2003)
Gildea, D., Jurafsky, D.: Automatic labelling of semantic roles. In: Proceedings of 38th Annual Conference of the Association for Computational Linguistics (ACL-00), pp. 512–520. ACL, San Francisco (2000)
Guarino, N.: Formal ontology in information systems. In: Guarino, N. (ed.) Formal Ontology in Information Systems. Proceedings of FOIS98, Trento, pp. 3–15. IOS, Amsterdam (1998)
Hayes, P.J.: The second naïve physics manifesto. In: Hobbes, J., Moore, R. (eds.) Formal Theories of the Common Sense World. Ablex Publishing Corporation, Norwood (1985)
Laird, J.E.: The SOAR Cognitive Architecture. MIT, Cambridge/London (2012)
Lenat, D.G., Prakash, M., Sheperd, M.: Cyc: using common sense knowledge to overcome brittleness and knowledge acquisition bottlenecks. Artif. Intell. 6(4), 65–85 (1985)
Maitikanen, P., Sukthankar, R., Hebert, M.: Feature seeding for action recognition. In: Proceedings of International Conference on Computer Vision. IEEE, Piscataway (2011)
Majid, A., Boster, J., Bowerman, M.: The cross-linguistic categorization of everyday events: a study of cutting and breaking. Cognition 109, 235–250 (2008)
Masolo, C., Gangemi, A., Guarino, N., Oltramari, A., Schneider, L.: WonderWeb deliverable D17: the Wonderweb library of foundational ontologies. Tech. rep. (2002)
McCarthy, J.: Circumscription – a form of non-monotonic reasoning. Artif. Intell. 5(13), 27–39 (1980)
Miller, G.A., Buckhout, R.: Psychology: The Science of Mental Life. Harper & Row, New York (1973)
Minsky, M.: A framework for representing knowledge. In: Winston, P. (ed.) Mind Design, pp. 111–142. MIT, Cambridge (1997)
Newell, A.: Unified Theories of Cognition. Harvard University Press, Cambridge (1990)
Newell, A., Shaw, J., Simon, H.: Report on a general problem-solving program. In: Proceedings of the International Conference on Information Processing, pp. 256–264. Unesco, Paris (1959)
Oltramari, A.: Lexipass methodology: a conceptual path from frames to senses and back. In: LREC 2006 (Fifth International Conference on Language Resources and Evaluation). ELDA, Genoa (2006)
Pedersen, T., Patwardhan, S.J., Michelizzi, M.: Wordnet: similarity: measuring the relatedness of concepts. In: Demonstration Papers at HLT-NAACL, pp. 38–41. ACL. East Stroudsburg (2004)
Prev́ot, L., Huang, C.R., Calzolari, N., Gangemi, A., Lenci, A., Oltramari, A. (eds.): Ontology and the Lexicon. Cambridge University Press, Cambridge/New York (2010)
Ruppenhofer, J., Ellsworth, M., Petruck, M., Johnson, C.: Framenet: Theory and Practice. ICSI, Berkeley (2005)
Schooler, L., Anderson, J.: The disruptive potential of immediate feedback. In: Proceedings of the Twelfth Annual Conference of The Cognitive Science Society, pp. 702–708. Erlbaum, Hillsdale (1990)
Simons, P. (ed.): Parts: A Study in Ontology. Clarendon, Oxford (1987)
Singer, P.W.: Wired for War. Penguin, New York (2009)
Siskind, J.M.: Grounding language in perception. Artif. Intell. Rev. 8, 371–391 (1995)
Sowa, J.F.: Conceptual Structures. Information Processing in Mind and Machine. Addison Wesley, Reading (1984)
Stocco, A., Lebiere, C., Anderson, J.: Conditional routing of information to the cortex: a model of the basal ganglia’s role in cognitive coordination. Psychol. Rev. 117(2), 541–574 (2010)
Tversky, A.: Features of similarity. Psychol. Rev. 84, 327–352 (1977)
Tversky, B., Zachs, J., Martin, B.: The structure of experience. In: Shipley, T., Zacks, T. (eds.) Understanding Events: From Perception to Action, pp. 436–464. Oxford University Press, Oxford/New York (2008)
Acknowledgements
This research was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-10-2-0061. 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 Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Oltramari, A., Lebiere, C. (2013). Knowledge in Action: Integrating Cognitive Architectures and Ontologies. In: Oltramari, A., Vossen, P., Qin, L., Hovy, E. (eds) New Trends of Research in Ontologies and Lexical Resources. Theory and Applications of Natural Language Processing. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31782-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-31782-8_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31781-1
Online ISBN: 978-3-642-31782-8
eBook Packages: Computer ScienceComputer Science (R0)