2016

Label-Free Supervision of Neural Networks with Physics and Domain Knowledge

Stewart, Russell, Ermon, Stefano

Understand

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive.

  • We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than direct examples of input-output pairs.
  • These constraints are derived from prior domain knowledge, e.g., from known laws of physics.
  • We demonstrate the effectiveness of this approach on real world and simulated computer vision tasks.

Built on

Nothing clear enough to list yet.

Similar

  • Learning compact binary descriptors with unsupervised deep neural networks

    Lin, K.; Lu, J.; Chen, C.-S.; and Zhou, J

    Cited in the paper.

Then

Nothing clear enough to list yet.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…