Lemmy: Bestiverse
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS BotMB to Lobste.rsEnglish · 5 hours ago

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (2021)

arxiv.org

external-link
message-square
0
fedilink
2
external-link

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (2021)

arxiv.org

RSS BotMB to Lobste.rsEnglish · 5 hours ago
message-square
0
fedilink
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
arxiv.org
external-link
The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer vision, playing Go, or protein folding -- are in fact feasible with appropriate computational scale. Remarkably, the essence of deep learning is built from two simple algorithmic principles: first, the notion of representation or feature learning, whereby adapted, often hierarchical, features capture the appropriate notion of regularity for each task, and second, learning by local gradient-descent type methods, typically implemented as backpropagation. While learning generic functions in high dimensions is a cursed estimation problem, most tasks of interest are not generic, and come with essential pre-defined regularities arising from the underlying low-dimensionality and structure of the physical world. This text is concerned with exposing these regularities through unified geometric principles that can be applied throughout a wide spectrum of applications. Such a 'geometric unification' endeavour, in the spirit of Felix Klein's Erlangen Program, serves a dual purpose: on one hand, it provides a common mathematical framework to study the most successful neural network architectures, such as CNNs, RNNs, GNNs, and Transformers. On the other hand, it gives a constructive procedure to incorporate prior physical knowledge into neural architectures and provide principled way to build future architectures yet to be invented.

Comments

alert-triangle
You must log in or register to comment.

Lobste.rs

lobsters

Subscribe from Remote Instance

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !lobsters@lemmy.bestiver.se
lock
Community locked: only moderators can create posts. You can still comment on posts.

RSS Feed of lobste.rs

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 34 users / day
  • 104 users / week
  • 380 users / month
  • 1.28K users / 6 months
  • 2 local subscribers
  • 252 subscribers
  • 7.57K Posts
  • 377 Comments
  • Modlog
  • mods:
  • patrick
  • RSS Bot
  • BE: 0.19.5
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org