Enhanced image classification with a fast-learning shallow convolutional neural network

Proceedings of the International Joint Conference on Neural Networks

Volumn 2015-September, Issue , 2015, Pages

  McDonnell, Mark D ^a   Vladusich, Tony ^a  

^a UNIVERSITY OF SOUTH AUSTRALIA   (Australia)

Author keywords

Databases

Indexed keywords

CLASSIFICATION (OF INFORMATION); COMPLEX NETWORKS; CONVOLUTION; DATABASE SYSTEMS; ERRORS; ITERATIVE METHODS; NETWORK ARCHITECTURE; NEURAL NETWORKS;

BIOLOGICALLY INSPIRED; CONVOLUTIONAL NEURAL NETWORK; IMPLEMENTATION COMPLEXITY; LEAST SQUARES REGRESSION; LINEAR CLASSIFIERS; STATE-OF-THE-ART METHODS; TRAINING METHODS; VISUAL-PROCESSING;

IMAGE CLASSIFICATION;

EID: 84951097371     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2015.7280796     Document Type: Conference Paper

References (35)

1. J. Schmidhuber, "Deep learning in neural networks: An overview, " Neural Networks, vol. 61, pp. 85-117, 2015.
2. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition, " Proceedings of the IEEE, vol. 86, pp. 2278-2324, 1998.
3. A. Coates, H. Lee, and A. Y. Ng, "An analysis of single-layer networks in unsupervised feature learning, " in Proc. }4th International Coriference on Artificial Intelligence and Statistics (AISTATS), 20}}, Fort Lauderdale, F L, USA. Volume 15 of JMLR:W&CP 15, 2011.
4. A Coates and A. Y. Ng, "The importance of encoding versus training wIth sparse coding and vector quantization, " in Proceedings of the 28th International Coriference on Machine Learning (ICML), Bellevue, WA, USA, 2011.
5. Q. V. Le, 1. Ngiam, Z. Chen, D. Chia, P. W. Koh, and A. Y. Ng, "Tiled convolutional neural networks, " in Advances in Neural Information Processing Systems 23, 1. Lafferty, C. Williams, J. Shawe-Taylor, R. Zemel, and A. Culotta, Eds., 2010, pp. 1279-1287.
6. P. F. Schmidt, M. A. Kraaijveld, and R. P. W. Duin, "Feed forward neural networks with random weights, " in Proc. 11 th IAPR Int. Conf on Pattern Recognition, Volume fl, Conf B: Pattern Recognition Methodology and Systems (ICPR) 1, T he Hague, Aug. 30-Sep. 3), IEEE Computer Society Press, Los Alamitos, CA, 1992, 1-4, 1992.
7. C. L. P. Chen, "A rapid supervised learning neural network for function interpolation and approximation, " IEEE Transactions on Neural Networks, vol. 7, pp. 1220-1230, 1996.
8. C. Eliasmith and C. H. Anderson, Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems. MIT P ress, Cambridge, MA, 2003.
9. G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, "Extreme learning machine: A new learning scheme of feed forward neural networks, " in In Proc. International Joint Conference on Neural Networks (lJCNN'2004), (Budapest, Hungary), July 25-29, 2004.
10. C. Eliasmith, T. C. Stewart, X. Choo, T. Bekolay, T. DeWolf, C. Tang, and D. Rasmussen, "A large-scale model of the functioning brain, " Science, vol. 338, pp. 1202-1205, 2012.
11. T. C. Stewart and C. Eliasmith, "Large-scale synthesis of functional spiking neural circuits, " Proceedings of the IEEE, vol. 102, pp. 881-898, 2014.
12. G.-B. Huang, H. Zhou, X. Ding, and R. Zhang, "Extreme learning machine for regression and multi class classification, " IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, vol. 42, pp. 513-529, 2012.
13. G.-B. Huang, "An insight into extreme learning machines: Random neurons, random features and kernels, " Cognitive Computation, vol. 6, pp. 376-390, 2014.
14. M. D. McDonnell, M. D. Tissera, T. V ladusich, A. van Schaik, and J. Tapson, "Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the 'extreme learning machine' algorithm, " P LOS One, vol. 10, e0134254 (1-20), 2015.
15. A. van Schaik and J. Tapson, "Online and adaptive pseudo inverse solutions for ELM weights, " Neurocomputing, vol. 149, pp. 233-238, 2015.
16. J. Tapson, P. de Chazal, and A. van Schaik, "Explicit computation of input weights in extreme learning machines, " in Proc. ELM2014 coriference, 2014, arXiv: 1406. 2889.
17. D. Yu and L. Ding, "Efficient and effective algorithms for training single-hidden-layer neural networks, " Pattern Recognition Letters, vol. 33, pp. 554-558, 2012.
18. W. Zhu, J. Miao, and L. Qing, "Constrained extreme learning machine: A novel highly discriminative random feedforward neural network, " in Proc. lJCNN, 2014, p. XXX.
19. -, "Constrained extreme learning machines: A study on classification cases, " 2015, arXiv: 1501. 06115.
20. Y. LeCun, C. Cortes, and C. J. C. Burges, "The MNIST database of handwritten digits;' Accessed July 2015, http://yann. lecun. com/exdb/mnist/.
21. A. Krizhevsky, "Learning multiple layers of features from tiny images, " Master's thesis, Dept of CS, University of Toronto. See http://www. cs. Toronto. edu/ kriz/ cifar. html), 2009.
22. Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, "Reading digits in natural images with unsupervised feature learning, " 2011, niPS Workshop on Deep Learning and Unsupervised Feature Learning. See http://ufldl. stanford. edu/housenumbers.
23. Y. LeCun, F. J. Huang, and L. Bottou, "Learning methods for generic object recognition with invariance to pose and lighting, " in Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, 2004, pp. 97-104.
24. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, "Overfeat: Integrated recognition, localization and detection using convolutional networks, " in International Conference on Learning Representations (ICLR 2014). CBLS, 2014.
25. P. Sermanet, S. Chintala, and Y. LeCun, "Convolutional neural networks applied to house numbers digit classification, " in International Conference on Pattern Recognition (ICPR), 2012.
26. P. Sermanet, "A deep learning pipeline for image understanding and acoustic modeling, " Ph. D. dissertation, Department of Computer Science, New York University., 2014.
27. J. Maira, P. Koniusz, Z. Harchaoui, and C. Schmid, "Convolutional kernel networks, " in Advances in Neural Iriformation Processing Systems, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, Eds., vol. 27, 2014, pp. 2627-2635.
28. C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, "Deeply-supervised nets, " in Deep Learning and Representation Learning Workshop, NIPS, 2014.
29. D. C. D. Cirean, U. Meier, J. Masci, L. M. Gambardella, and J. Schmidhuber, "Flexible, high performance convolutional neural networks for image classification, " in Proceedings of the Twenty-Second International Joint Coriference on Artificial Intelligence, 2011, pp. 1237-1242.
30. P. Y. Simard, D. Steinkraus, and J. C. Platt, "Best practices for convolutional neural networks applied to visual document analysis, " in Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), 2003.
31. D. Cirean, U. Meier, L. M. Gambardella, and 1. Schmidhuber, "Deep, big, simple neural nets for handwritten digit recognition, " Neural Computation, vol. 22, pp. 3207-3220, 2010.
32. D. Cirean, U. Meier, and J. Schmidhuber, "Multi-Column deep neural networks for image classification, " in Proc. CVPR, 2012, pp. 3642-3649.
33. J. Tapson and A. van Schaik, "Learning the pseudoinverse solution to network weights, " Neural Networks, vol. 45, pp. 94-100, 2013.
34. B. Widrow, A. Greenblatt, Y. Kim, and D. Park, "The No-Prop algorithm: A new learning algorithm for multilayer neural networks, " Neural Networks, vol. 37, pp. 182-188, 2013.
35. G.-B. Huang, Z. Bai, L. L. C. Kasun, and C. M. Vong, "Local receptive fields based extreme learning machine, " IEEE Computational Intelligence Magazine, vol. 10, pp. 18-29, 2015.