Convex Neural Networks
| Type of publication: | Inproceedings |
| Citation: | NIPS2005_583 |
| Booktitle: | Advances in Neural Information Processing Systems 18 (NIPS'05) |
| Year: | 2006 |
| Pages: | 123--130 |
| Publisher: | MIT Press |
| Address: | Cambridge, MA |
| Crossref: | NIPS18: |
| URL: | http://www.iro.umontreal.ca/~l... |
| Abstract: | 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, each time finding a linear classifier that minimizes a weighted sum of errors. |
| Userfields: | topics={Boosting},cat={C}, |
| Keywords: | |
| Authors | |
| Editors | |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
