Generalization Bounds For Deep Convolutional Neural Networks
ASecurity
**arXiv ID:** 1905.12600 **Authors:** Philip M. Long, Hanie Sedghi **Published:** 2019-05-29T17:20:36Z **Abstract:** We prove bounds on the generalization error of convolutional networks. The bounds are in terms of the training loss, the number of parameters, the Lipschitz constant of the loss and the distance from the weights to the initial weights. They are independent of the number of pixels in the input, and the height and width of hidden feature maps. We present experiments using CIFAR-1...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Generalization Bounds For Deep Convolutional Neural Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-generalization-bounds-for-deep-convolutional-neura)
# Generalization bounds for deep convolutional neural networks
**arXiv ID:** 1905.12600
**Authors:** Philip M. Long, Hanie Sedghi
**Published:** 2019-05-29T17:20:36Z
**Abstract:**
We prove bounds on the generalization error of convolutional networks. The bounds are in terms of the training loss, the number of parameters, the Lipschitz constant of the loss and the distance from the weights to the initial weights. They are independent of the number of pixels in the input, and the height and width of hidden feature maps. We present experiments using CIFAR-10 with varying hyperparameters of a deep convolutional network, comparing our bounds with practical generalization gaps.
## Skill Description
This skill is generated from the arXiv paper: Generalization bounds for deep convolutional neural networks (1905.12600).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1905.12600](http://arxiv.org/abs/1905.12600v6)