AI RESEARCH

Batch Normalization for Neural Networks on Complex Domains

arXiv CS.LG

ArXi:2605.00467v1 Announce Type: new Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normalization (BN) layers have shown to enhance