# Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

arXiv: https://arxiv.org/abs/1812.05836 · HTML: https://mlsanity.com/paper/1812.05836/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2018.

## Built on by (most cited first, 1 of 1)

- [FedCC: Robust Federated Learning against Model Poisoning Attacks](https://mlsanity.com/paper/2212.01976/) (2022)

## Abstract (arXiv)

We characterize convolutional neural networks with respect to the relative amount of features per layer. Using a skew normal distribution as a parametrized framework, we investigate the common assumption of monotonously increasing feature-counts with higher layers of architecture designs. Our evaluation on models with VGG-type layers on the MNIST, Fashion-MNIST and CIFAR-10 image classification benchmarks provides evidence that motivates rethinking of our common assumption: architectures that favor larger early layers seem to yield better accuracy.