In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
Abstract
We present experiments demonstrating that some other form of capacity control, different from network size, plays a central role in learning multilayer feed-forward networks. We argue, partially through analogy to matrix factorization, that this is an inductive bias that can help shed light on deep learning.
Cite
Text
Neyshabur et al. "In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning." International Conference on Learning Representations, 2015.Markdown
[Neyshabur et al. "In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning." International Conference on Learning Representations, 2015.](https://mlanthology.org/iclr/2015/neyshabur2015iclr-search/)BibTeX
@inproceedings{neyshabur2015iclr-search,
title = {{In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning}},
author = {Neyshabur, Behnam and Tomioka, Ryota and Srebro, Nathan},
booktitle = {International Conference on Learning Representations},
year = {2015},
url = {https://mlanthology.org/iclr/2015/neyshabur2015iclr-search/}
}