TY - STD TI - Agostinelli F, Hoffman M, Sadowski P, Baldi, P. Learning activation functions to improve deep neural networks. 2014. arXiv preprint, arXiv:1412.6830. UR - http://arxiv.org/abs/1412.6830 ID - ref1 ER - TY - CHAP AU - Ba, J. AU - Frey, B. ED - Burges, C. J. ED - Bottou, L. ED - Welling, M. ED - Ghahramani, Z. ED - Weinberger, K. Q. PY - 2013 DA - 2013// TI - Adaptive dropout for training deep neural networks BT - Advances in neural information processing systems PB - Curran CY - Red Hook ID - Ba2013 ER - TY - BOOK AU - Bishop, C. M. PY - 1995 DA - 1995// TI - Neural networks for pattern recognition PB - Oxford University Press CY - Oxford ID - Bishop1995 ER - TY - STD TI - Clevert D-A, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). In: Proceedings of the 4th international conference on learning representations. 2016. p. 1–14. ID - ref4 ER - TY - STD TI - Collobert R, Bengio S. A gentle Hessian for efficient gradient descent. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing. 2004. p. 517–20. ID - ref5 ER - TY - STD TI - Farfade SS, Saberian MJ, Li L-J. Multi-view face detection using deep convolutional neural networks. In: 5th international conference on multimedia retrieval. New York: ACM. 2015. p. 643–50. ID - ref6 ER - TY - JOUR AU - Fei-Fei, L. AU - Fergus, R. AU - Perona, P. PY - 2006 DA - 2006// TI - One-shot learning of object categories JO - IEEE Trans Pattern Anal Mach Intell VL - 28 UR - https://doi.org/10.1109/TPAMI.2006.79 DO - 10.1109/TPAMI.2006.79 ID - Fei-Fei2006 ER - TY - STD TI - Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th international conference on artificial intelligence and statistics. 2010. p. 249–56. ID - ref8 ER - TY - CHAP AU - Gong, Y. u. n. c. h. a. o. AU - Wang, L. i. w. e. i. AU - Guo, R. u. i. q. i. AU - Lazebnik, S. v. e. t. l. a. n. a. PY - 2014 DA - 2014// TI - Multi-scale Orderless Pooling of Deep Convolutional Activation Features BT - Computer Vision – ECCV 2014 PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-10584-0_26 DO - 10.1007/978-3-319-10584-0_26 ID - Gong2014 ER - TY - STD TI - Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y. Maxout networks. In: Proceedings of the 30th international conference machine learning. 2013. p. 1319–27. ID - ref10 ER - TY - STD TI - Graham B. Fractional max-pooling. 2014. arXiv preprint, arXiv:1412.6071. UR - http://arxiv.org/abs/1412.6071 ID - ref11 ER - TY - STD TI - Grauman K, Darrell T. The pyramid match kernel: discriminative classification with sets of image features. In: Proceedings of the IEEE international conference on computer vision. Red Hook: Curran; 2005. p. 1458–65. ID - ref12 ER - TY - BOOK AU - Griffin, G. AU - Holub, A. AU - Perona, P. PY - 2007 DA - 2007// TI - Caltech-256 object category dataset PB - California University of Technology CY - Pasadena ID - Griffin2007 ER - TY - JOUR AU - Hashemi, M. PY - 2019 DA - 2019// TI - Web page classification: a survey of perspectives, gaps, and future directions JO - Multimed Tools Appl UR - https://doi.org/10.1007/s11042-019-08373-8 DO - 10.1007/s11042-019-08373-8 ID - Hashemi2019 ER - TY - JOUR AU - Hashemi, M. AU - Hall, M. PY - 2019 DA - 2019// TI - Detecting and classifying online dark visual propaganda JO - Image Vis Comput VL - 89 UR - https://doi.org/10.1016/j.imavis.2019.06.001 DO - 10.1016/j.imavis.2019.06.001 ID - Hashemi2019 ER - TY - BOOK AU - Haykin, S. S. PY - 1999 DA - 1999// TI - Neural networks: a comprehensive foundation PB - Prentice Hall CY - Upper Saddle River ID - Haykin1999 ER - TY - STD TI - He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. Red Hook: Retrieved from Curran; 2015. p. 1026–34. ID - ref17 ER - TY - JOUR AU - He, K. AU - Zhang, X. AU - Ren, S. AU - Sun, J. PY - 2015 DA - 2015// TI - Spatial pyramid pooling in deep convolutional networks for visual recognition JO - IEEE Trans Pattern Anal Mach Intell VL - 37 UR - https://doi.org/10.1109/TPAMI.2015.2389824 DO - 10.1109/TPAMI.2015.2389824 ID - He2015 ER - TY - STD TI - He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the ieee conference on computer vision and pattern recognition. 2016. p. 770–8. ID - ref19 ER - TY - CHAP AU - He, K. AU - Zhang, X. AU - Ren, S. AU - Sun, J. PY - 2016 DA - 2016// TI - Identity mappings in deep residual networks BT - European conference on computer vision PB - Springer CY - Cham ID - He2016 ER - TY - STD TI - Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR. Improving neural networks by preventing co-adaptation of feature detectors. 2012. arXiv preprint, arXiv:1207.0580. UR - http://arxiv.org/abs/1207.0580 ID - ref21 ER - TY - STD TI - Huang G, Liu Z, Maaten LV, Weinberger KQ. Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 4700–8. ID - ref22 ER - TY - STD TI - Jin X, Xu C, Feng J, Wei Y, Xiong J, Yan S. Deep learning with s-shaped rectified linear activation units. In: 13th AAAI conference on artificial intelligence. 2016. ID - ref23 ER - TY - STD TI - Kingma DP, Ba J. Adam: a method for stochastic optimization. 2014. arXiv preprint, arXiv:1412.6980. UR - http://arxiv.org/abs/1412.6980 ID - ref24 ER - TY - STD TI - Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in Neural information processing systems. 2012. p. 1097–105. ID - ref25 ER - TY - STD TI - Laptev D, Savinov N, Buhmann JM, Pollefeys M. TI-POOLING: transformation-invariant pooling for feature learning in convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 289–97. ID - ref26 ER - TY - STD TI - Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Red Hook: Curran; 2006. p. 2169–78. ID - ref27 ER - TY - STD TI - Lee C-Y, Gallagher PW, Tu Z. Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree. In: Proceedings of the 19th international conference on artificial intelligence and statistics. 2016. p. 464–72. ID - ref28 ER - TY - STD TI - Li Z, Gong B, Yang T. Improved dropout for shallow and deep learning. In: Lee D, Sugiyama M, Luxburg UV, Guyon I, Garnett R, editors. Advances in neural information processing systems. 2016. p. 2523–31. ID - ref29 ER - TY - STD TI - Lin M, Chen Q, Yan S. Network in network. 2013. arXiv preprint, arXiv:1312.4400. UR - http://arxiv.org/abs/1312.4400 ID - ref30 ER - TY - STD TI - Liu W, Wen Y, Yu Z, Yang M. Large-margin softmax loss for convolutional neural networks. In: Proceedings of the 33rd international conference machine learning, vol. 2. 2016. p. 507–16. ID - ref31 ER - TY - STD TI - Maas AL, Hannun AY, Ng AY. Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th international conference machine learning, vol. 30. 2013. p. 1–8. ID - ref32 ER - TY - STD TI - Mishkin D, Matas J. All you need is a good init. In Proceedings of the 4th international conference on learning representations. 2016. p. 1–13. ID - ref33 ER - TY - STD TI - Nagi J, Caro GA, Giusti A, Nagi F, Gambardella LM. Convolutional neural support vector machines: hybrid visual pattern classifiers for multi-robot systems. In: Proceedings of the 11th international conference on machine learning and applications. Los Alamitos: IEEE; 2012. p. 27–32. ID - ref34 ER - TY - STD TI - Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: The 27th international conference on machine learning. 2010. p. 807–14. ID - ref35 ER - TY - STD TI - National Data Science Bowl | Kaggle. 2016. https://www.kaggle.com/c/datasciencebowl. UR - https://www.kaggle.com/c/datasciencebowl ID - ref36 ER - TY - STD TI - Rippel O, Gelbart M, Adams R. Learning ordered representations with nested dropout. In: Proceedings of the 30th international conference on machine learning. 2014. p. 1746–54. ID - ref37 ER - TY - CHAP AU - Rippel, O. AU - Snoek, J. AU - Adams, R. P. ED - Cortes, C. ED - Lawrence, N. D. ED - Lee, D. D. ED - Sugiyama, M. ED - Garnett, R. PY - 2015 DA - 2015// TI - Spectral representations for convolutional neural networks BT - Advances in neural information processing systems PB - Curran CY - Red Hook ID - Rippel2015 ER - TY - JOUR AU - Russakovsky, O. AU - Deng, J. AU - Su, H. AU - Krause, J. AU - Satheesh, S. AU - Ma, S. AU - Huang, Z. AU - Karpathy, A. AU - Khosla, A. AU - Bernstein, M. AU - Berg, A. C. PY - 2015 DA - 2015// TI - ImageNet large scale visual recognition challenge JO - Int J Comput Vis VL - 115 UR - https://doi.org/10.1007/s11263-015-0816-y DO - 10.1007/s11263-015-0816-y ID - Russakovsky2015 ER - TY - STD TI - Sermanet P, Chintala S, LeCun Y. Convolutional neural networks applied to house numbers digit classification. In: Proceedings of the 21st international conference on pattern recognition. Red Hook: Curran; 2012. p. 3288–91. ID - ref40 ER - TY - STD TI - Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv preprint, arXiv:1409.1556. UR - http://arxiv.org/abs/1409.1556 ID - ref41 ER - TY - STD TI - Springenberg JT, Riedmiller M. Improving deep neural networks with probabilistic maxout units. 2013. arXiv preprint, arXiv:1312.6116. UR - http://arxiv.org/abs/1312.6116 ID - ref42 ER - TY - JOUR AU - Srivastava, N. G. AU - Krizhevsky, A. AU - Sutskever, I. AU - Salakhutdinov, R. PY - 2014 DA - 2014// TI - Dropout: a simple way to prevent neural networks from overfitting JO - J Mach Learn Res VL - 15 ID - Srivastava2014 ER - TY - CHAP AU - Srivastava, R. K. AU - Greff, K. AU - Schmidhuber, J. ED - Cortes, C. ED - Lawrence, N. D. ED - Lee, D. D. ED - Sugiyama, M. ED - Garnett, R. PY - 2015 DA - 2015// TI - Training very deep networks BT - Advances in neural information processing systems PB - Curran CY - Red Hook ID - Srivastava2015 ER - TY - STD TI - Srivastava RK, Greff K, Schmidhuber J. Highway networks. 2015. arXiv preprint, arXiv:1505.00387. UR - http://arxiv.org/abs/1505.00387 ID - ref45 ER - TY - STD TI - Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition. New York: IEEE; 2015. p. 1–9. ID - ref46 ER - TY - STD TI - Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. p. 2818–26. ID - ref47 ER - TY - STD TI - Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C. Efficient object localization using convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Los Alamitos: IEEE; 2015. p. 648–56. ID - ref48 ER - TY - STD TI - Wan L, Zeiler M, Zhang S, Cun YL, Fergus R. Regularization of neural networks using Dropconnect. In: Proceedings of the 30th international conference machine learning. 2013. p. 1058–66. ID - ref49 ER - TY - JOUR AU - Wang, M. AU - Liu, X. AU - Wu, X. PY - 2015 DA - 2015// TI - Visual classification by l1-hypergraph modeling JO - IEEE Trans Knowl Data Eng VL - 27 UR - https://doi.org/10.1109/TKDE.2015.2415497 DO - 10.1109/TKDE.2015.2415497 ID - Wang2015 ER - TY - STD TI - Wang S, Manning C. Fast dropout training. In: Proceedings of the 30th international conference on machine learning. 2013. p. 118–26. ID - ref51 ER - TY - STD TI - Werbos PJ. Beyond regression: new tools for prediction and analysis in the behavioral sciences. Cambridge: Ph.D. Thesis, Harvard University; 1974. ID - ref52 ER - TY - CHAP AU - Wu, H. a. i. b. i. n. g. AU - Gu, X. i. a. o. d. o. n. g. PY - 2015 DA - 2015// TI - Max-Pooling Dropout for Regularization of Convolutional Neural Networks BT - Neural Information Processing PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-26532-2_6 DO - 10.1007/978-3-319-26532-2_6 ID - Wu2015 ER - TY - STD TI - Yang J, Yu K, Gong Y, Huang TS. Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol. 1. Red Hook: Curran; 2009. p. 1794–801. ID - ref54 ER - TY - CHAP AU - Yu, D. i. n. g. j. u. n. AU - Wang, H. a. n. l. i. AU - Chen, P. e. i. q. i. u. AU - Wei, Z. h. i. h. u. a. PY - 2014 DA - 2014// TI - Mixed Pooling for Convolutional Neural Networks BT - Rough Sets and Knowledge Technology PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-11740-9_34 DO - 10.1007/978-3-319-11740-9_34 ID - Yu2014 ER - TY - JOUR AU - Yu, J. AU - Tao, D. AU - Wang, M. PY - 2012 DA - 2012// TI - Adaptive hypergraph learning and its application in image classification JO - IEEE Trans Image Process VL - 21 UR - https://doi.org/10.1109/TIP.2012.2190083 DO - 10.1109/TIP.2012.2190083 ID - Yu2012 ER - TY - STD TI - Zeiler MD, Fergus R. Stochastic pooling for regularization of deep convolutional neural networks. 2013. arXiv preprint, arXiv:1301.3557. UR - http://arxiv.org/abs/1301.3557 ID - ref57 ER - TY - CHAP AU - Zeiler, M. a. t. t. h. e. w. D. AU - Fergus, R. o. b. PY - 2014 DA - 2014// TI - Visualizing and Understanding Convolutional Networks BT - Computer Vision – ECCV 2014 PB - Springer International Publishing CY - Cham UR - https://doi.org/10.1007/978-3-319-10590-1_53 DO - 10.1007/978-3-319-10590-1_53 ID - Zeiler2014 ER - TY - STD TI - Zeiler MD, Taylor GW, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning. In: Proceedings of the IEEE international conference on computer vision, vol. 1. Red Hook: Curran; 2011. p. 2018–25. ID - ref59 ER - TY - STD TI - Zhai S, Cheng Y, Zhang ZM, Lu W. Doubly convolutional neural networks. In: Lee D, Sugiyama M, Luxburg UV, Guyon I, Garnett R, editors. Advances in neural information processing systems. vol. 29. 2016. p. 1082–90. ID - ref60 ER -