# Shared Representational Geometry Across Neural Networks

arXiv: https://arxiv.org/abs/1811.11684 · HTML: https://mlsanity.com/paper/1811.11684/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

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

- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [StitchNet: Composing Neural Networks from Pre-Trained Fragments](https://mlsanity.com/paper/2301.01947/) (2023)

## Abstract (arXiv)

Different neural networks trained on the same dataset often learn similar input-output mappings with very different weights. Is there some correspondence between these neural network solutions? For linear networks, it has been shown that different instances of the same network architecture encode the same representational similarity matrix, and their neural activity patterns are connected by orthogonal transformations. However, it is unclear if this holds for non-linear networks. Using a shared response model, we show that different neural networks encode the same input examples as different orthogonal transformations of an underlying shared representation. We test this claim using both standard convolutional neural networks and residual networks on CIFAR10 and CIFAR100.