A Model of Heteroassociative Memory: Deciphering Surprising Features and Locations: Unterschied zwischen den Versionen

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche
(Eine dazwischenliegende Version desselben Benutzers wird nicht angezeigt)
(kein Unterschied)

Aktuelle Version vom 13. November 2015, 00:24 Uhr


Shashank Bhatia and Stephan Chalup: A Model of Heteroassociative Memory: Deciphering Surprising Features and Locations. In: Computational Creativity 2013 ICCC 2013, 139-146.



The identification of surprising or interesting locations in an environment is an important problem in the fields of robotics (localisation, mapping and exploration), ar- chitecture (wayfinding, design), navigation (landmark identification) and computational creativity. Despite this familiarity, existing studies are known to rely ei- ther on human studies (in architecture and navigation) or complex feature intensive methods (in robotics) to evaluate surprise. In this paper, we propose a novel het- eroassociative memory architecture that remembers in- put patterns along with features associated with them. The model mimics human memory by comparing and associating new patterns with existing patterns and fea- tures, and provides an account of surprise experienced. The application of the proposed memory architecture is demonstrated by identifying monotonous and surprising locations present in a Google Sketchup model of an en- vironment. An inter-disciplinary approach combining the proposed memory model and isovists (from archi- tecture) is used to perceive and remember the structure of different locations of the model environment. The experimental results reported describe the behaviour of the proposed surprise identification technique, and illus- trate the universal applicability of the method. Finally, we also describe how the memory model can be modi- fied to mimic forgetfulness.

Extended Abstract


author = {Shashank Bhatia and Stephan Chalup},
title = {A Model of Heteroassociative Memory: Deciphering Surprising Features and Locations},
editor = {Simon Colton, Dan Ventura, Nada Lavrac, Michael Cook},
booktitle = {Proceedings of the Fourth International Conference on Computational Creativity},
series = {ICCC2013},
year = {2013},
month = {Jun},
location = {Sydney, New South Wales, Australia},
pages = {139-146},
url = {http://www.computationalcreativity.net/iccc2013/download/iccc2013-bhatia-chalup.pdf, http://de.evo-art.org/index.php?title=A_Model_of_Heteroassociative_Memory:_Deciphering_Surprising_Features_and_Locations },
publisher = {International Association for Computational Creativity},
keywords = {computational, creativity},

Used References

Albright, T. D. 2012. On the Perception of Probable Things: Neural Substrates of Associative Memory, Imagery, and Per- ception. Neuron 74(2):227–245.

Baldi, P., and Ittii, L. 2010. Of bits and wows: A Bayesian theory of surprise with applications to attention. Neural Net- works 23(5):649–666.

Bartlett, M. S. 1952. The statistical significance of odd bits of information. Biometrika 39:228–237.

Benedikt, M. 1979. To take hold of space: isovists and isovist fields. Environment and Planning B: Planning and Design 6(1):47–65.

Bhatia, S.; Chalup, S. K.; and Ostwald, M. J. 2012. Ana- lyzing Architectural Space: Identifying Salient Regions by Computing 3D Isovists. In Proceedings of 46th Annual Con- ference of the Architectural Science Association, ASA 2012.

Brown, D. C. 2012. Creativity, Surprise & Design: An Intro- duction and Investigation. The 2nd International Conference on Design Creativity (ICDC2012) 1:75–86.

Carlson, L. A.; H ̈olscher, C.; Shipley, T. F.; and Conroy- Dalton, R. 2010. Getting Lost in Buildings. Current Direc- tions in Psychological Science 19(5):284–289.

Cole, D., and Harrison, A. 2005. Using Naturally Salient Regions for SLAM with 3D Laser Data. In In Proceedings of International Conference on Robotics and Automation, Workshop on SLAM.

Good, I. J. 1956. The surprise index for the multivariate normal distribution. The Annals of Mathematical Statistics 27(4):1130–1135.

Itti, L., and Baldi, P. 2009. Bayesian surprise attracts human attention. Vision Research 49(10):1295–1306.

Kendall, D. G. 1989. A survey of the statistical theory of shape. Statistical Science 4(2):87–89.

Kosko, B. 1988. Bidirectional associative memories. IEEE Transactions on Systems, Man, and Cybernetics 18(1):49– 60.

Kullback, S. 1997. Information theory and statistics. Dover Publications.

Palm, G. 2013. Neural associative memories and sparse coding. Neural Networks 37:165–171.

Perttula, A.; Carter, S.; and Denoue, L. 2009. Kartta: ex- tracting landmarks near personalized points-of-interest from user generated content. Proceedings of the 11th Inter- national Conference on Human-Computer Interaction with Mobile Devices and Services 72.

Ranganathan, A., and Dellaert, F. 2009. Bayesian surprise and landmark detection. In 2009 IEEE International Con- ference on Robotics and Automation (ICRA), 2017–2023. IEEE.

Redheffer, R. M. 1951. A note on the surprise index. The Annals of Mathematical Statistics 22(1):128–130.

Shannon, C. E. 2001. A Mathematical Theory of Commu- nication. ACM SIGMOBILE Mobile Computing and Com- munications Review 5(1):3–55.

Siagian, C., and Itti, L. 2009. Biologically Inspired Mobile Robot Vision Localization. IEEE Transactions on Robotics 25(4):861–873.

Trimble. 2013. Google Sketchup. Retrieved from http://sketchup.google.com/intl/en/.

Weaver, W. 1966. Probability, rarity, interest, and surprise. Pediatrics 38(4):667–670.

Xia, J. C.; Arrowsmith, C.; Jackson, M.; and Cartwright, W. 2008. The wayfinding process relationships between decision-making and landmark utility. Tourism Management 29(3):445–457.

Zhang, L.; Tong, M. H.; and Cottrell, G. W. 2009. SUN- DAy: Saliency using natural statistics for dynamic analysis of scenes. In Proceedings of the 31st Annual Cognitive Sci- ence Conference, 2944–2949.


Full Text


intern file

Sonstige Links