# Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change

arXiv: https://arxiv.org/abs/2011.06735 · HTML: https://mlsanity.com/paper/2011.06735/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2020.

## Built on by (most cited first, 2 of 2)

- [Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks](https://mlsanity.com/paper/2102.06604/) (2021)
- [WeightScale: Interpreting Weight Change in Neural Networks](https://mlsanity.com/paper/2107.07005/) (2021)

## Abstract (arXiv)

Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep Convolutional Neural Networks (CNNs) by measuring the relative weight change of layers while training. Several interesting trends emerge in a variety of CNN architectures across various computer vision classification tasks, including the overall increase in relative weight change of later layers as compared to earlier ones.