Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them

21 March 2024

Papers citing "Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them"

3 / 3 papers shown

Title
How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching András Balogh Márk Jelasity 85 0 0 15 Dec 2024
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 252 313 0 11 Sep 2022
Aggregated Residual Transformations for Deep Neural Networks Saining Xie Ross B. Girshick Piotr Dollár Z. Tu Kaiming He 297 10,216 0 16 Nov 2016