Abstract
In order to allow more flexible and general learning, it is an advantage for artificial systems to be able to discover re-usable features that capture structure in the environment, known as Deep Learning. Techniques have been shown based on convolutional neural networks and stacked Restricted Boltzmann Machines, which are related to some degree with neural processes. An alternative approach using abstract representations, the ARCS Learning Classifier System, has been shown to build feature hierarchies based on reinforcement, providing a different perspective, however with limited classification performance compared to Artificial Neural Network systems. An Abstract Deep Network is presented that is based on ARCS for building the feature network, and introduces gradient descent to allow improved results on an image classification task. A number of implementations are examined, comparing the use of back-propagation at various depths of the system. The ADN system is able to produce classification error of 1.18% on the MNIST dataset, comparable with the most established general learning systems on this task. The system shows strong reliability in constructing features, and the abstract representation provides a good platform for studying further effects such as as top-down influences.
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
Bengio, Y., Courville, A.C., Vincent, P.: Unsupervised feature learning and deep learning: A review and new perspectives. CoRR abs/1206.5538 (2012)
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2009)
Rousselet, G.A., Thorpe, S.J., Fabre-Thorpe, M.: How parallel is visual processing in the ventral pathway? Trends in Cognitive Sciences 8(8), 363–370 (2004)
Serre, T., Kreiman, G., Kouh, M., Cadieu, C., Knoblich, U., Poggio, T.: A quantitative theory of immediate visual recognition. In: Paul Cisek, T.D., Kalaska, J.F. (eds.) Computational Neuroscience: Theoretical Insights into Brain Function. Progress in Brain Research, vol. 165, pp. 33–56. Elsevier (2007)
Weng, J.: A 5-chunk developmental brain-mind network model for multiple events in complex backgrounds. In: IJCNN, pp. 1–8 (July 2010)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010)
Fischer, A., Igel, C.: Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS, vol. 6354, pp. 208–217. Springer, Heidelberg (2010)
Desjardins, G., Courville, A., Bengio, Y., Vincent, P., Delalleau, O.: Tempered Markov Chain Monte Carlo for training of restricted Boltzmann machines. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Chia Laguna Resort, Sardinia, Italy, May 13-15, pp. 145–152 (2010)
Urbanowicz, R.J., Moore, J.H.: Learning classifier systems: a complete introduction, review, and roadmap. J. Artif. Evol. App. 2009, 1:1–1:25 (2009)
Knittel, A.: An activation reinforcement based classifier system for balancing generalisation and specialisation (ARCS). In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 1871–1878. ACM, New York (2010)
Anderson, J.R., Bothell, D., Byrne, M.D., Douglass, S., Lebiere, C., Qin, Y.: An integrated theory of the mind. Psychological Review 111(4), 1036–1060 (2004)
Knittel, A.: Learning feature hierarchies under reinforcement. In: IEEE Congress on Evolutionary Computation (CEC). IEEE (2012)
Ebadi, T., Zhang, M., Browne, W.: XCS-based versus UCS-based feature pattern classification system. In: Proceedings of the Fourteenth International Conference on Genetic and Evolutionary Computation Conference, GECCO 2012, pp. 839–846. ACM, New York (2012)
Haykin, S.: Neural networks and learning machines. Prentice Hall (2009)
Bar, M.: A cortical mechanism for triggering top-down facilitation in visual object recognition. J. Cognitive Neuroscience 15(4), 600–609 (2003)
Bar, M.: Visual objects in context. Nature Reviews Neuroscience 5(8), 617–629 (2004)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Ranzato, M., Huang, F.J., Boureau, Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: CVPR 2007, pp. 1–8 (June 2007)
Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: ICML, pp. 609–616. ACM, New York (2009)
Grauman, K., Leibe, B.: Visual Object Recognition. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Knittel, A., Blair, A.D. (2012). An Abstract Deep Network for Image Classification. In: Thielscher, M., Zhang, D. (eds) AI 2012: Advances in Artificial Intelligence. AI 2012. Lecture Notes in Computer Science(), vol 7691. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35101-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-35101-3_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35100-6
Online ISBN: 978-3-642-35101-3
eBook Packages: Computer ScienceComputer Science (R0)