ML Anthology

AdaNet: Adaptive Structural Learning of Artificial Neural Networks

Corinna Cortes, Xavier Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
ICML 2017 pp. 874-883
/icml/2017/cortes2017icml-adanet/

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.

PDF ICML Semantic Scholar

Cite

Text

Cortes et al. "AdaNet: Adaptive Structural Learning of Artificial Neural Networks." International Conference on Machine Learning, 2017.

Markdown

[Cortes et al. "AdaNet: Adaptive Structural Learning of Artificial Neural Networks." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/cortes2017icml-adanet/)

BibTeX

@inproceedings{cortes2017icml-adanet,
  title     = {{AdaNet: Adaptive Structural Learning of Artificial Neural Networks}},
  author    = {Cortes, Corinna and Gonzalvo, Xavier and Kuznetsov, Vitaly and Mohri, Mehryar and Yang, Scott},
  booktitle = {International Conference on Machine Learning},
  year      = {2017},
  pages     = {874-883},
  volume    = {70},
  url       = {https://mlanthology.org/icml/2017/cortes2017icml-adanet/}
}