Abstract
I propose a learning and memory architecture which can incrementally learn and associate an increasing number of patterns. The approach consists of the integration of two methods – a topology learning algorithm to perform incremental clustering, and an associative memory model to learn relationships based on the co-occurrence of input patterns. The approach supports online learning, is tolerant to noise, and generally applicable to any kind of real-valued vector data. I tested the proposed architecture on an incremental associative learning task with visual patterns. Evaluations were performed both in a simulated setup and with a real robot. Results showed that the architecture could learn nearly all presented patterns but in some cases the recall rate decreased as these patterns were retrieved. I suggest ways to overcome this effect and also discuss future work aimed at achieving a better performance.
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
Preview
Unable to display preview. Download preview PDF.
References
Balkenius, C., Morén, J.: Computational models of classical conditioning: A comparative study. Tech. rep., Lund University Cognitive Science (1998)
Bouchachia, A.: Evolving clustering: An asset for evolving systems. IEEE SMC – eNewsletter (36) (September 2011)
Bouchachia, A., Lughofer, E., Sayed-Mouchaweh, M.: Editorial to the special issue: Evolving soft computing techniques and applications. Applied Soft Computing 14, 141–143 (2014)
Bouchachia, A., Vanaret, C.: Incremental learning based on growing gaussian mixture models. In: Proceedings of the 10th International Conference on Machine Learning and Applications (ICMLA 2011), pp. 47–52 (2011)
Deng, D., Kasabov, N.: On-line pattern analysis by evolving self-organizing maps. Neurocomputing 51, 87–103 (2003)
Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems 7, pp. 625–632. MIT Press (1995)
Fritzke, B.: A self-organizing network that can follow non-stationary distributions. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 613–618. Springer, Heidelberg (1997)
Furao, S., Hasegawa, O.: An incremental network for on-line unsupervised classification and topology learning. Neural Networks 19, 90–106 (2006)
Furao, S., Ogura, T., Hasegawa, O.: An enhanced self-organizing incremental neural network for online unsupervised learning. Neural Networks 20, 893–903 (2007)
Furao, S., Ouyang, Q., Kasai, W., Hasegawa, O.: A general associative memory based on self-organizing incremental neural network. Neurocomputing 104, 57–71 (2013)
Gama, J.: Knowledge Discovery from Data Streams. Data Mining and Knowledge Discovery Series. Chapman & Hall/CRC (2010)
Hebb, D.O.: The Organization of Behavior – A Neuropsychological Theory. John Wiley & Sons (1949)
Keysermann, M.U., Vargas, P.A.: Desiderata for a memory model. In: Proceedings of the 12th UK Workshop on Computational Intelligence, pp. 37–44 (2012)
Lughofer, E.: A dynamic split-and-merge approach for evolving cluster models. Evolving Systems 3(3), 135–151 (2012)
Marsland, S., Shapiro, J., Nehmzow, U.: A self-organising network that grows when required. Neural Networks 15(8), 1041–1058 (2002)
O’Reilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience - Understanding the Mind by Simulating the Brain. MIT Press (2000)
Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press (1999)
Prudent, Y., Ennaji, A.: An incremental growing neural gas learns topologies. In: Proceedings of the 2005 IEEE International Joint Conference on Neural Network (IJCNN 2005), vol. 2, pp. 1211–1216 (2005)
Rescorla, R.A., Wagner, A.R.: A theory of pavlovian conditioning: Variations in the effectiveness of reinforcement and nonreinforcement. In: Classical Conditioning II: Current Theory and Research, pp. 64–99. Appleton-Century-Crofts (1972)
Sayed-Mouchaweh, M., Lughofer, E.: Learning in Non-Stationary Environments – Methods and Applications. Springer, New York (2012)
Sudo, A., Sato, A., Hasegawa, O.: Associative memory for online learning in noisy environments using self-organizing incremental neural network. IEEE Transactions on Neural Networks 20(6), 964–972 (2009)
Tangruamsub, S., Kawewong, A., Tsuboyama, M., Hasegawa, O.: Self-organizing incremental associative memory-based robot navigation. IEICE Transactions on Information and Systems E95-D(10), 2415–2425 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Keysermann, M.U. (2014). ICALA: Incremental Clustering and Associative Learning Architecture. In: Bouchachia, A. (eds) Adaptive and Intelligent Systems. ICAIS 2014. Lecture Notes in Computer Science(), vol 8779. Springer, Cham. https://doi.org/10.1007/978-3-319-11298-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-11298-5_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11297-8
Online ISBN: 978-3-319-11298-5
eBook Packages: Computer ScienceComputer Science (R0)