Poster "residual networks" Papers
2 papers found
Conference
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Yu Pan, Chaozheng Wang, Zekai Wu et al.
ICLR 2025arXiv:2503.04626
6
citations
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
Peter Súkeník, Christoph Lampert, Marco Mondelli
NEURIPS 2025arXiv:2505.15239
4
citations