Deep Learning and Machine Learning in Imaging: Basic Principles
Artificial intelligence has recently received much attention largely because of substantial improvements in image recognition performance, based largely on a class of algorithms known as deep learning. Prior machine learning methods are still useful and can provide a good understanding of machine learning fundamentals. Deep learning methods are still seeing rapid advances, but there are several basic components that are likely to be durable. This chapter describes the concepts common to all machine learning and then provides a more detailed description of deep learning methods and components.
KeywordsConvolutional neural network Deep learning Support vector machine Feature vector Neural network
- 1.Vapnik V. Pattern recognition using generalized portrait method. Autom Remote Control. 1963;24:774–80.Google Scholar
- 2.Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory – COLT ’92. 1992. https://doi.org/10.1145/130385.130401 .
- 3.Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273–97.Google Scholar
- 5.Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Pereira F, CJC B, Bottou L, Weinberger KQ, editors. Advances in neural information processing systems 25. Red Hook, NY: Curran Associates; 2012. p. 1097–105.Google Scholar
- 6.Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv [cs.CV].Google Scholar
- 7.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Computer vision and pattern recognition (CVPR). 2015. http://arxiv.org/abs/1409.4842
- 8.He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Bajcsy, editor. Proceedings of the IEEE conference on computer visions and pattern recognition. Los Alamitos, CA: Conference Publishing Services; 2016. p. 770–8.Google Scholar
- 9.Xie S, Girshick R, Dollár P, Tu Z, He K. Aggregated residual transformations for deep neural networks. 2016. arXiv [cs.CV]. Google Scholar
- 10.Ren S, He K, Girshick R, Sun J. Faster R-CNN: towards real-time object detection with region proposal networks. 2015. arXiv [cs.CV].Google Scholar
- 11.Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF, editors. Medical image computing and computer-assisted intervention – MICCAI 2015. Cham: Springer International Publishing; 2015. p. 234–41.CrossRefGoogle Scholar
- 12.Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. 2015. arXiv [cs.CV].Google Scholar
- 13.LeCun Y, Boser BE, Denker JS, Henderson D, Howard RE, Hubbard WE, Jackel LD. Handwritten digit recognition with a back-propagation network. In: Touretzky DS, editor. Advances in neural information processing systems 2. San Mateo, CA: Morgan-Kaufmann; 1990. p. 396–404.Google Scholar
- 14.Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ, editors. Advances in neural information processing systems 27. Red Hook, NY: Curran Associates; 2014. p. 2672–80.Google Scholar