Flexible, high performance convolutional neural networks for image classification
作者： Dan C. Cireşan , Jonathan Masci , Jürgen Schmidhuber , Luca M. Gambardella , Ueli Meier
DOI: 10.5591/978-1-57735-516-8/IJCAI11-210
关键词:
摘要: We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in supervised way. deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB completely within five epochs. Test MNIST drop to 2.42%, 0.97% 0.48% after 1, 3 17 epochs,
ijcai.org
idsia.ch
acm.org 参考文章(29)
Sven Behnke, Hierarchical Neural Networks for Image Interpretation (Lecture Notes in Computer Science) Springer-Verlag New York, Inc.. ,(2003)
Dominik Scherer, Andreas Müller, Sven Behnke, None, Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition Artificial Neural Networks – ICANN 2010. pp. 92- 101 ,(2010) , 10.1007/978-3-642-15825-4_10
Kumar Chellapilla, Sidd Puri, Patrice Simard, High Performance Convolutional Neural Networks for Document Processing international conference on frontiers in handwriting recognition. ,(2006)
Sven Behnke, Hierarchical Neural Networks for Image Interpretation ,(2003)
T. Serre, L. Wolf, T. Poggio, Object recognition with features inspired by visual cortex computer vision and pattern recognition. ,vol. 2, pp. 994- 1000 ,(2005) , 10.1109/CVPR.2005.254
Jim Mutch, David G. Lowe, Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields computer vision and pattern recognition. ,vol. 80, pp. 45- 57 ,(2008) , 10.1007/S11263-007-0118-0
Daniel Strigl, Klaus Kofler, Stefan Podlipnig, Performance and Scalability of GPU-Based Convolutional Neural Networks parallel, distributed and network-based processing. pp. 317- 324 ,(2010) , 10.1109/PDP.2010.43
Jürgen Schmidhuber, Martin Eldracher, Bernhard Foltin, Semilinear predictability minimization produces well-known feature detectors Neural Computation. ,vol. 8, pp. 773- 786 ,(1996) , 10.1162/NECO.1996.8.4.773
Kunihiko Fukushima, Neocognitron: A Self Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position Biological Cybernetics. ,vol. 36, pp. 193- 202 ,(1980) , 10.1007/BF00344251
D. H. Hubel, T. N. Wiesel, Receptive fields of single neurones in the cat's striate cortex The Journal of Physiology. ,vol. 148, pp. 574- 591 ,(1959) , 10.1113/JPHYSIOL.1959.SP006308