Abstract
Artificial neural networks have been widely used for machine learning tasks such as object recognition. Recent developments have made use of biologically inspired architectures, such as the Convolutional Neural Network. The nature of the Convolutional Neural Network is that each convolutional layer of the network contains a certain number of feature maps or kernels. The number of these used has historically been determined on an ad-hoc basis. We propose a theoretical method for determining the optimal number of feature maps using the dimensions of the feature map or convolutional kernel. We find that the empirical data suggests that our theoretical method works for extremely small receptive fields, but doesn’t generalize as clearly to all receptive field sizes. Furthermore, we note that architectures that are pyramidal rather than equally balanced tend to make better use of computational resources.
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
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: A CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference, June 2010, SciPy (2010) oral Presentation
Boureau, Y.L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 111–118 (2010)
Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649. IEEE (2012)
Coates, A., Ng, A.Y., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)
Eigen, D., Rolfe, J., Fergus, R., LeCun, Y.: Understanding Deep Architectures using a Recursive Convolutional Network. ArXiv e-prints (December 2013)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: IEEE CVPR 2004, Workshop on Generative-Model Based Vision (2004)
Fukushima, K., Miyake, S.: Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recognition 15(6), 455–469 (1982)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in a cats visual cortex. Journal of Physiology (London) 160, 106–154 (1962)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25, 1106–1114 (2012)
LeCun, Y., Bottou, L., Bengio, Y.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
LeCun, Y., Huang, F., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 97–104 (2004)
Nguyen, G.H., Phung, S.L., Bouzerdoum, A.: Reduced training of convolutional neural networks for pedestrian detection. In: International Conference on Information Technology and Applications (2009)
Scherer, D., Schulz, H., Behnke, S.: Accelerating large-scale convolutional neural networks with parallel graphics multiprocessors. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS, vol. 6354, pp. 82–91. Springer, Heidelberg (2010)
Simard, P., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: ICDAR, vol. 3, pp. 958–962 (2003)
Uetz, R., Behnke, S.: Large-scale object recognition with cuda-accelerated hierarchical neural networks. In: IEEE International Conference on Intelligent Computing and Intelligent Systems, ICIS 2009, vol. 1, pp. 536–541. IEEE (2009)
Uetz, R., Behnke, S.: Locally-connected hierarchical neural networks for gpu-accelerated object recognition. In: NIPS 2009 Workshop on Large-Scale Machine Learning: Parallelism and Massive Datasets (2009)
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
Chu, J.L., Krzyżak, A. (2014). Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks. In: Sokolova, M., van Beek, P. (eds) Advances in Artificial Intelligence. Canadian AI 2014. Lecture Notes in Computer Science(), vol 8436. Springer, Cham. https://doi.org/10.1007/978-3-319-06483-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-06483-3_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06482-6
Online ISBN: 978-3-319-06483-3
eBook Packages: Computer ScienceComputer Science (R0)