Deep Learning - Activations, Convolutions, and Pooling Part 4

This video presents max and average pooling, introduces the concept of fully convolutional networks, and hints on how this is used to build deep networks.

References:
[1] I. J. Goodfellow, D. Warde-Farley, M. Mirza, et al. “Maxout Networks”. In: ArXiv e-prints (Feb. 2013). arXiv: 1302.4389 [stat.ML].
[2] Kaiming He, Xiangyu Zhang, Shaoqing Ren, et al. “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification”. In: CoRR abs/1502.01852 (2015). arXiv: 1502.01852.
[3] Günter Klambauer, Thomas Unterthiner, Andreas Mayr, et al. “Self-Normalizing Neural Networks”. In: Advances in Neural Information Processing Systems (NIPS). Vol. abs/1706.02515. 2017. arXiv: 1706.02515.
[4] Min Lin, Qiang Chen, and Shuicheng Yan. “Network In Network”. In: CoRR abs/1312.4400 (2013). arXiv: 1312.4400.
[5] Andrew L. Maas, Awni Y. Hannun, and Andrew Y. Ng. “Rectifier Nonlinearities Improve Neural Network Acoustic Models”. In: Proc. ICML. Vol. 30. 1. 2013.
[6] Prajit Ramachandran, Barret Zoph, and Quoc V. Le. “Searching for Activation Functions”. In: CoRR abs/1710.05941 (2017). arXiv: 1710.05941.
[7] Stefan Elfwing, Eiji Uchibe, and Kenji Doya. “Sigmoid-weighted linear units for neural network function approximation in reinforcement learning”. In: arXiv preprint arXiv:1702.03118 (2017).
[8] Christian Szegedy, Wei Liu, Yangqing Jia, et al. “Going Deeper with Convolutions”. In: CoRR abs/1409.4842 (2014). arXiv: 1409.4842.

Further Reading:
A gentle Introduction to Deep Learning