Improvising the Learning of Neural Networks on Hyperspherical Manifold

1 code implementation • 29 Sep 2021 • Lalith Bharadwaj Baru, Sai Vardhan Kanumolu, Akshay Patel Shilhora, Madhu G

First, the stereographic projection is implied to transform data from Euclidean space ($\mathbb{R}^{n}$) to hyperspherical manifold ($\mathbb{S}^{n}$) to analyze the performance of angular margin losses.

Face Identification Face Recognition +1