Bayesian representation learning with oracle constraints

@inproceedings{Karaletsos2015BayesianRL,
  title={Bayesian representation learning with oracle constraints},
  author={Theofanis Karaletsos and Serge Belongie and Gunnar Ratsch},
  year={2015}
}
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria. However, the semantic structure inherent in observations is oftentimes lost in the process. Human perception excels at understanding semantics but cannot always be expressed in terms of labels… CONTINUE READING
Highly Cited
This paper has 30 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 37 times over the past 90 days. VIEW TWEETS
22 Citations
26 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 22 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 26 references

Similar Papers

Loading similar papers…