Corpus ID: 9343698

Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network

@article{Piekniewski2016UnsupervisedLF,
  title={Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network},
  author={Filip Piekniewski and Patryk A. Laurent and Csaba Petre and Micah Richert and Dimitry Fisher and Todd Hylton},
  journal={ArXiv},
  year={2016},
  volume={abs/1607.06854}
}
  • Filip Piekniewski, Patryk A. Laurent, +3 authors Todd Hylton
  • Published 2016
  • Computer Science
  • ArXiv
  • Understanding visual reality involves acquiring common-sense knowledge about countless regularities in the visual world, e.g., how illumination alters the appearance of objects in a scene, and how motion changes their apparent spatial relationship. These regularities are hard to label for training supervised machine learning algorithms; consequently, algorithms need to learn these regularities from the real world in an unsupervised way. We present a novel network meta-architecture that can… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 15 CITATIONS

    Integrating Motion into Vision Models for Better Visual Prediction

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    Toward an Integration of Deep Learning and Neuroscience

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Saccadic Predictive Vision Model with a Fovea

    VIEW 6 EXCERPTS
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 114 REFERENCES

    Unsupervised Visual Representation Learning by Context Prediction

    Anticipating Visual Representations from Unlabeled Video

    VIEW 2 EXCERPTS

    Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

    VIEW 2 EXCERPTS

    Visual Tracking with Fully Convolutional Networks

    VIEW 1 EXCERPT