DeapSECURE module 4: Deep Learning (Neural Network): Credits for materials used

Image credits

• Image of network of neurons, posted at Max Pixel

  https://www.maxpixel.net/Neurons-Brain-Structure-Network-Brain-Cells-Brain-440660 This image is in public domain. license of Creative Commons Zero CC0. Use this image with referral.

• Image of a neuron, by Wikipedia user BruceBlaus

  https://en.wikipedia.org/wiki/Neuron#/media/File:Blausen_0657_MultipolarNeuron.png Author is BruceBlaus. This work is free and may use by anyone. CC BY 3.0 https://creativecommons.org/licenses/by/3.0/

• Color image of a fully-connected neural network with one hidden layer, by Wikimedia user Glosser.ca

  https://en.wikipedia.org/wiki/Artificial_neural_network#/media/File:Colored_neural_network.svg https://commons.wikimedia.org/wiki/File:Colored_neural_network.svg CC BY-SA 3.0

  Modified by WP to match the fill color to conventions used by Asimov Institute’s neural network zoo.

• Overfitting illustration, by Wikimedia user Chabacano

  https://en.wikipedia.org/wiki/Overfitting#/media/File:Overfitting.svg CC BY-SA 4.0 This image is free to share and adapt.

• Dropout illustration

  Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.

• Resnet introduction

  He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).