Convex Neural Networks

  title={Convex Neural Networks},
  author={Yoshua Bengio and Nicolas Le Roux and Pascal Vincent and Olivier Delalleau and Patrice Marcotte},
Convexity has recently received a lot of attention in the machine learning community, and the lack of convexity has been seen as a major disadvantage of many learning algorithms, such as multi-layer artificial neural networks. We show that training multi-layer neural networks in which the number of hidden units is learned can be viewed as a convex optimization problem. This problem involves an infinite number of variables, but can be solved by incrementally inserting a hidden unit at a time… CONTINUE READING
Highly Cited
This paper has 86 citations. REVIEW CITATIONS


Publications citing this paper.

86 Citations

Citations per Year
Semantic Scholar estimates that this publication has 86 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 15 references

Linear Programming

  • V. Chvátal
  • W.H. Freeman.
  • 1983
Highly Influential
5 Excerpts

Least absolute shrinkage is equivalent to quadratic penalization

  • Y. Grandvalet
  • 1998

Similar Papers

Loading similar papers…