# Improvising the Learning of Neural Networks on Hyperspherical Manifold

Source: [Improvising the Learning of Neural Networks on Hyperspherical Manifold](<https://www.sota2.com/research/paper/68fa6de31e209131cea3cac5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:45:11.347Z

Authors: Lalith Bharadwaj Baru, Sai Vardhan Kanumolu, Akshay Patel Shilhora, Madhu G

Published: 2021-09-29T22:39:07.000Z

## Abstract

The impact of convolution neural networks (CNNs) in the supervised settings provided tremendous increment in performance. The representations learned from CNN's operated on hyperspherical manifold led to insightful outcomes in face recognition, face identification, and other supervised tasks. A broad range of activation functions were developed with hypersphere intuition which performs superior to softmax in euclidean space. The main motive of this research is to provide insights. 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. Secondly, proving theoretically and practically that decision boundaries constructed on hypersphere using stereographic projection obliges the learning of neural networks. Experiments have demonstrated that applying stereographic projection on existing state-of-the-art angular margin objective functions improved performance for standard image classification data sets (CIFAR-10,100). Further, we ran our experiments on malaria-thin blood smear images, resulting in effective outcomes. The code is publicly available at:https://github.com/barulalithb/stereo-angular-margin.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.14746>)

[PDF](<https://arxiv.org/pdf/2109.14746.pdf>)
