Subspace Match Probably Does Not Accurately Assess the Similarity of Learned Representations

3 January 2019

Papers citing "Subspace Match Probably Does Not Accurately Assess the Similarity of Learned Representations"

2 / 2 papers shown

Title
Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction Konstantin Schurholt Dimche Kostadinov Damian Borth SSL 119 15 0 28 Oct 2021
An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks Konstantin Schurholt Damian Borth 98 3 0 18 Jun 2020