← Front page

The TWIML AI Podcast · Monday, July 27, 2026

Addressing Permutation Symmetries in Neural Network Weights

Damian Borth highlights the challenge of permutation symmetries in neural network weights, where changing the order of neurons doesn't alter the network's function. His team developed techniques like contrastive loss and augmentation strategies to address these symmetries in weight space learning.

personDamian Borth

The tape

3 quotes
One of the tricky things with weight spaces is, when you have a neural network and you have two layers, let's say for simplicity, fully connected, you can change the position of the neurons and, uh, it's actually changes the sequence of the neurons, the order of weights, but the function is the same.
Damian Borth
So, you know, there are a lot of permutation symmetries and other, you know, symmetries that, you know, in the weight space that do not change the underlying function.
Damian Borth
So we have already in the first paper, we had contrastive loss, and to build a contrast, you need to augment. So, I mean, it's simple to flip an image or rotate an image, but you know, what's the counterparty in weight space?
Damian Borth
Heard on The TWIML AI Podcast — “Why Models Are AI’s Next Training Dataset with Damian Borth - #772, published Monday, July 27, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.05
Addressing Permutation Symmetries in Neural Network Weights — Heardvine