2017

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

Bojarski, Mariusz, Yeres, Philip, Choromanska, Anna et al.

Understand

As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead.

  • PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car.
  • It derives the necessary domain knowledge by observing human drivers.
  • This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving.

Built on

  • Backpropagation applied to handwritten zip code recognition

    Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel · 1989

    Earlier work this paper cites.

  • How to explain individual classification decisions

    D. Baehrens, T. Schroeter, S. Harmeling, M.i Kawanabe, K. Hansen, and K.-R. Müller · 2010

    Earlier work this paper cites.

  • Adaptive deconvolutional networks for mid and high level feature learning

    M. D. Zeiler, G. W. Taylor, and R. Fergus · 2011

    Earlier work this paper cites.

Similar

  • Visualization of nonlinear classification models in neuroimaging - signed sensitivity maps

    P. M. Rasmussen, T. Schmah, K. H. Madsen, T. E. Lund, S. C. Strother, and L. K. Hansen · 2012

    Cited alongside, same era.

  • Deep inside convolutional networks: Visualising image classification models and saliency maps

    K. Simonyan, A. Vedaldi, and A. Zisserman · 2014

    Cited alongside, same era.

  • Visualizing and understanding convolutional networks

    M. D. Zeiler and R. Fergus · 2014

    Cited alongside, same era.

Then

  • On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation

    S. Bach, A. Binder, G. Montavon, F. Klauschen, K.-R. Müller, and W Samek · 2015

    Later among the works it cites.

  • End to end learning for self-driving cars, April 25 2016

    Original

    Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, and Karol Zieba · 2016

    Later among the works it cites.

  • VisualBackProp: visualizing CNNs for autonomous driving, November 16 2016

    Original

    Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Bernhard Firner, Larry Jackel, Urs Muller, and Karol Zieba · 2016

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…