Data:

• Some data from Autonomoustuff; 5G or so from a recent drive. This data is in a ROS bag (link should help sort things out)
• A small tarfile of likely useful code for reading the bag
• A bag of mobileye data from Autonomoustuff
• A bag of general data collected on a long run from Autonomoustuff (just over 6G)
• Another bag of general data collected on a long run from Autonomoustuff all sensors, rather big
• A bag of data collected in a highway construction region from Autonomoustuff all sensors, huge
• A bag of data collected in a run from Morton to Washington (?) at dusk on a long run from Autonomoustuff all sensors, huge
• A bag of data collected on a run down Green street from Autonomoustuff all sensors, huge

Papers

Resources:

• Summarised Deep Learning Notes, D.A. Forsyth, (approximate 9'th draft) Version of 18 Jan 2017
• Rough notes by D.A. Forsyth on: variational methods, multidimensional scaling, and auto-encoders for 29 Mar, 6 April
• Very nice Stanford course notes from CS231N
• Tensorflow download install
• Tensorflow tutorials
• MATCONVNET download and getting started and documentation
• MATCONVNET tutorial by Andrea Vedaldi and Andrew Zisserman
• ROS download and tutorial
• Some material on using GTA for training reinforcement learners

• Deep network topics

  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Sergey Ioffe, Christian Szegedy
  • Dropout: A Simple Way to Prevent Neural Networks from Overfitting Nitish Srivastava Geoffrey Hinton Alex Krizhevsky Ilya Sutskever Ruslan Salakhutdinov
  • Swapout: Learning an ensemble of deep architectures Saurabh Singh, Derek Hoiem, David Forsyth
  • Tensorflow
  • MatConvNet

• Object detection

  • Faster {R-CNN}: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren and Kaiming He and Ross Girshick and Jian Sun

• Pedestrian detection

  • Ten Years of Pedestrian Detection, What Have We Learned? Rodrigo Benenson, Mohamed Omran, Jan Hosang, Bernt Schiele
  • How Far are We from Solving Pedestrian Detection? Shanshan Zhang and Rodrigo Benenson and Mohamed Omran and Jan Hosang and Bernt Schiele
  • Caltech (and other) Pedestrian Detection Datasets

• Traffic Signs

  • Traffic-Sign Detection and Classification in the Wild Zhe Zhu, Dun Liang, Songhai Zhang, Xiaolei Huang, Baoli Li, Shimin Hu
  • German Traffic Sign Recognition benchmark
  • German Traffic Sign Detection benchmark
  • Multi-Column Deep Neural Network for Traffic Sign Classification Dan Cire ̧san, Ueli Meier, Jonathan Masci and Ju ̈rgen Schmidhuber

• Adversarial examples

  • Explaining and Harnessing Adversarial Examples Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy
  • Intriguing properties of neural networks Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus
  • Adversarial Manipulation of Deep Representations Sara Sabour, Yanshuai Cao, Fartash Faghri, David J. Fleet
  • Introspective perception: Learning to predict failures in vision systems S Daftry, S Zeng, JA Bagnell, M Hebert

• Inverse reinforcement learning

  • Pieter Abbeel's slides on IRL
  • Learning to search: Functional Gradient Techniques for Inverse Reinforcement Learning N. Ratliff, D. Silver, J.A. Bagnell

• Autoencoding

  • Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion Pascal Vincent Hugo Larochelle Isabelle Lajoie Yoshua Bengio Pierre-Antoine Manzagol The Journal of Machine Learning Research archive Volume 11, 3/1/2010 Pages 3371-3408
  • Auto-Encoding Variational Bayes Diederik P Kingma, Max Welling, 2013 quite a tough read
  • Tutorial on Variational Autoencoders Carl Doersch nice tutorial by Carl Doersch
  • An Uncertain Future: Forecasting from Static Images using Variational Autoencoders Jacob Walker, Carl Doersch, Abhinav Gupta, Martial Hebert Conditional variational autoencoder applied to Optic Flow
  • Learning Temporal Transformations From Time-Lapse Videos Yipin Zhou, Tamara L. Berg Conditional variational autoencoder applied to future prediction
  • CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation Jiajun Lu, Aditya Deshpande, David Forsyth discussion of code collapse

• Adversarial training

  • Generative Adversarial Networks Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio Original adversarial training paper
  • BEGAN: Boundary Equilibrium Generative Adversarial Networks David Berthelot, Thomas Schumm, Luke Metz BEGAN (best current adversarial method, uses clever autoencoder trick for adversary)

• Style transfer

  • A Neural Algorithm of Artistic Style Leon A. Gatys, Alexander S. Ecker, Matthias Bethge Original style transfer paper
  • Image Style Transfer Using Convolutional Neural Networks, Leon A. Gatys Alexander S. Ecker Matthias Bethge, CVPR 2016more style transfer