AdaNet: Adaptive Structural Learning of Artificial Neural Networks

Corinna Cortes, Xavier Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:874-883, 2017.

Abstract

We present a new framework for analyzing and learning artificial neural networks. Our approach simultaneously and adaptively learns both the structure of the network as well as its weights. The methodology is based upon and accompanied by strong data-dependent theoretical learning guarantees, so that the final network architecture provably adapts to the complexity of any given problem.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-cortes17a, title = {{A}da{N}et: Adaptive Structural Learning of Artificial Neural Networks}, author = {Corinna Cortes and Xavier Gonzalvo and Vitaly Kuznetsov and Mehryar Mohri and Scott Yang}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {874--883}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/cortes17a/cortes17a.pdf}, url = {https://proceedings.mlr.press/v70/cortes17a.html}, abstract = {We present a new framework for analyzing and learning artificial neural networks. Our approach simultaneously and adaptively learns both the structure of the network as well as its weights. The methodology is based upon and accompanied by strong data-dependent theoretical learning guarantees, so that the final network architecture provably adapts to the complexity of any given problem.} }
Endnote
%0 Conference Paper %T AdaNet: Adaptive Structural Learning of Artificial Neural Networks %A Corinna Cortes %A Xavier Gonzalvo %A Vitaly Kuznetsov %A Mehryar Mohri %A Scott Yang %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-cortes17a %I PMLR %P 874--883 %U https://proceedings.mlr.press/v70/cortes17a.html %V 70 %X We present a new framework for analyzing and learning artificial neural networks. Our approach simultaneously and adaptively learns both the structure of the network as well as its weights. The methodology is based upon and accompanied by strong data-dependent theoretical learning guarantees, so that the final network architecture provably adapts to the complexity of any given problem.
APA
Cortes, C., Gonzalvo, X., Kuznetsov, V., Mohri, M. & Yang, S.. (2017). AdaNet: Adaptive Structural Learning of Artificial Neural Networks. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:874-883 Available from https://proceedings.mlr.press/v70/cortes17a.html.

Related Material