Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yingtao, Cerretti, Diego, Zhao, Jialin, Wu, Wenjing, Liao, Ziheng, Michieli, Umberto, Cannistraci, Carlo Vittorio
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.19107