By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
World of SoftwareWorld of SoftwareWorld of Software
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Search
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
Reading: Swarms on Manifolds for Deep Learning: Training Kuramoto Models and Trajectory Learning | HackerNoon
Share
Sign In
Notification Show More
Font ResizerAa
World of SoftwareWorld of Software
Font ResizerAa
  • Software
  • Mobile
  • Computing
  • Gadget
  • Gaming
  • Videos
Search
  • News
  • Software
  • Mobile
  • Computing
  • Gaming
  • Videos
  • More
    • Gadget
    • Web Stories
    • Trending
    • Press Release
Have an existing account? Sign In
Follow US
  • Privacy
  • Terms
  • Advertise
  • Contact
Copyright © All Rights Reserved. World of Software.
World of Software > Computing > Swarms on Manifolds for Deep Learning: Training Kuramoto Models and Trajectory Learning | HackerNoon
Computing

Swarms on Manifolds for Deep Learning: Training Kuramoto Models and Trajectory Learning | HackerNoon

News Room
Last updated: 2026/02/04 at 2:41 PM
News Room Published 4 February 2026
Share
Swarms on Manifolds for Deep Learning: Training Kuramoto Models and Trajectory Learning | HackerNoon
SHARE

Table of Links

Abstract and 1. Introduction

  1. Some recent trends in theoretical ML

    2.1 Deep Learning via continuous-time controlled dynamical system

    2.2 Probabilistic modeling and inference in DL

    2.3 Deep Learning in non-Euclidean spaces

    2.4 Physics Informed ML

  2. Kuramoto model

    3.1 Kuramoto models from the geometric point of view

    3.2 Hyperbolic geometry of Kuramoto ensembles

    3.3 Kuramoto models with several globally coupled sub-ensembles

  3. Kuramoto models on higher-dimensional manifolds

    4.1 Non-Abelian Kuramoto models on Lie groups

    4.2 Kuramoto models on spheres

    4.3 Kuramoto models on spheres with several globally coupled sub-ensembles

    4.4 Kuramoto models as gradient flows

    4.5 Consensus algorithms on other manifolds

  4. Directional statistics and swarms on manifolds for probabilistic modeling and inference on Riemannian manifolds

    5.1 Statistical models over circles and tori

    5.2 Statistical models over spheres

    5.3 Statistical models over hyperbolic spaces

    5.4 Statistical models over orthogonal groups, Grassmannians, homogeneous spaces

  5. Swarms on manifolds for DL

    6.1 Training swarms on manifolds for supervised ML

    6.2 Swarms on manifolds and directional statistics in RL

    6.3 Swarms on manifolds and directional statistics for unsupervised ML

    6.4 Statistical models for the latent space

    6.5 Kuramoto models for learning (coupled) actions of Lie groups

    6.6 Grassmannian shallow and deep learning

    6.7 Ensembles of coupled oscillators in ML: Beyond Kuramoto models

  6. Examples

    7.1 Wahba’s problem

    7.2 Linked robot’s arm (planar rotations)

    7.3 Linked robot’s arm (spatial rotations)

    7.4 Embedding multilayer complex networks (Learning coupled actions of Lorentz groups)

  7. Conclusion and References

6 Swarms on manifolds for DL

We have presented a broad class of models that generate trajectories on various manifolds. Given a particular setup, an appropriate model can be chosen and trained in order to learn an optimal (in a certain sense) trajectory on a specific manifold. Training these dynamical systems boils down to the estimation of parameters: coupling strengths, phase shifts, initial positions of (generalized) oscillators, etc. Noiseless models with global coupling generate trajectories on invariant statistical manifolds (wrapped Cauchy, spherical Cauchy, etc.). On the other hand, some important distributions (von Mises, hyperbolic von Mises, von Mises-Fisher) arise as stationary distributions in Kuramoto models with noise.

In this Section we briefly discuss ideas on implementation of the corresponding algorithms.

:::info
Author:

(1) Vladimir Jacimovic, Faculty of Natural Sciences and Mathematics, University of Montenegro Cetinjski put bb., 81000 Podgorica Montenegro ([email protected]).

:::


:::info
This paper is available on arxiv under CC by 4.0 Deed (Attribution 4.0 International) license.

:::

Sign Up For Daily Newsletter

Be keep up! Get the latest breaking news delivered straight to your inbox.
By signing up, you agree to our Terms of Use and acknowledge the data practices in our Privacy Policy. You may unsubscribe at any time.
Share This Article
Facebook Twitter Email Print
Share
What do you think?
Love0
Sad0
Happy0
Sleepy0
Angry0
Dead0
Wink0
Previous Article Google finally reveals Pixel 10a’s launch date Google finally reveals Pixel 10a’s launch date
Next Article Most employees aren't saving time with AI, even though CEOs think they are, report says Most employees aren't saving time with AI, even though CEOs think they are, report says
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Stay Connected

248.1k Like
69.1k Follow
134k Pin
54.3k Follow

Latest News

Debian’s Challenge When Its Developers Quietly Drift Away
Debian’s Challenge When Its Developers Quietly Drift Away
Computing
Democrats knock Bezos, decry Washington Post layoffs
Democrats knock Bezos, decry Washington Post layoffs
News
Top Cable Protectors for Sale: Unimat Solutions for Home, Office, and Events
Top Cable Protectors for Sale: Unimat Solutions for Home, Office, and Events
Gadget
One Identity Appoints Gihan Munasinghe as Chief Technology Officer | HackerNoon
One Identity Appoints Gihan Munasinghe as Chief Technology Officer | HackerNoon
Computing

You Might also Like

Debian’s Challenge When Its Developers Quietly Drift Away
Computing

Debian’s Challenge When Its Developers Quietly Drift Away

5 Min Read
One Identity Appoints Gihan Munasinghe as Chief Technology Officer | HackerNoon
Computing

One Identity Appoints Gihan Munasinghe as Chief Technology Officer | HackerNoon

3 Min Read
Mesa 26.0-rc3 Released With More Graphics Driver Fixes
Computing

Mesa 26.0-rc3 Released With More Graphics Driver Fixes

1 Min Read

Social Media Love Languages: Find Your Brand’s Content Style

1 Min Read
//

World of Software is your one-stop website for the latest tech news and updates, follow us now to get the news that matters to you.

Quick Link

  • Privacy Policy
  • Terms of use
  • Advertise
  • Contact

Topics

  • Computing
  • Software
  • Press Release
  • Trending

Sign Up for Our Newsletter

Subscribe to our newsletter to get our newest articles instantly!

World of SoftwareWorld of Software
Follow US
Copyright © All Rights Reserved. World of Software.
Welcome Back!

Sign in to your account

Lost your password?