Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
-
Updated
Nov 7, 2024 - Python
Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
Visualiser for basic geometric primitives and fractals in arbitrary-dimensional spaces
Implementation for <Orthogonal Over-Parameterized Training> in CVPR'21.
Code accompanying the paper "360 Surface Regression with a Hyper-Sphere Loss", 3DV 2019
Implementation for <Learning with Hyperspherical Uniformity> in AISTATS'21.
The Similarity Search Tree is an efficient method for indexing high dimensional feature vectors. The main objective of this data structure is to obtain the nearest neighbors given a certain query vector in a reasonable amount of time. In this project, the k-NN algorithm was adapted for supporting image retrieval.
Introduces a framework for making non-canonical hyperspherical coordinate systems.
montecarlo methods
Materials and code that I used for my bachelor thesis - Electrostatics and magnetostatics on a hypersphere
Hypersphere volume computation for low dimensionality using Monte Carlo techniques and threaded Ruby
Count and/or enumerate the lattice points that lie within a hypersphere
This document purpose is to demonstrate hyperspace volume in n dimensions.
Dedicated to exploring and understanding fascinating mathematical concepts that go beyond the basics. Whether you're a math enthusiast or someone looking to deepen your knowledge in intriguing areas of mathematics, this repository aims to provide resources and insights into the most captivating topics in the field.
Add a description, image, and links to the hypersphere topic page so that developers can more easily learn about it.
To associate your repository with the hypersphere topic, visit your repo's landing page and select "manage topics."