Equivariant Neural Networks | Part 1/3 - Introduction

▬▬ Papers / Resources ▬▬▬ Fabian Fuchs Equivariance: https://fabianfuchsml.github.io/equiv... Deep Learning for Molecules: https://dmol.pub/dl/Equivariant.html Naturally Occuring Equivariance: https://distill.pub/2020/circuits/equ... 3Blue1Brown Group Theory:    • Group theory, abstraction, and the 196,883...   Group Equivariant CNNs: https://arxiv.org/abs/1602.07576 Equivariance vs Data Augmentation: https://arxiv.org/pdf/2202.03990.pdf ▬▬ Used Music ▬▬▬▬▬▬▬▬▬▬▬ Music from #Uppbeat (free for Creators!): https://uppbeat.io/t/yokonap/birds License code: WXVHOOZRRWDUCKIU ▬▬ Used Icons ▬▬▬▬▬▬▬▬▬▬ All Icons are from flaticon: https://www.flaticon.com/authors/freepik ▬▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬ 00:00 Introduction 00:45 Equivariance and Invariance 03:03 CNNs are translation equivariant 04:00 Math notation 04:25 Visual intuition 05:08 Symmetries 06:22 Why are CNNs not rotation equivariant? 07:14 Inductive biases reduce the flexibility 08:10 What's wrong with data augmentations? 09:32 Motivations for Equivariant Neural Networks 09:55 You've unlocked a checkpoint. 10:07 Naturally occuring equivariance 10:50 Group Equivariant Convolutional Neural Networks 11:37 Group Theory (on a high level) 12:41 An example and the matrix notation 13:50 Group axioms 14:32 Cayley tables 15:33 Examples for groups 16:38 Applications of Equivariant Neural Networks 18:30 Final Checkpoint :) ▬▬ Support me if you like 🌟 ►Link to this channel: https://bit.ly/3zEqL1W ►Support me on Patreon: https://bit.ly/2Wed242 ►Buy me a coffee on Ko-Fi: https://bit.ly/3kJYEdl ►E-Mail: [email protected] ▬▬ My equipment 💻 Microphone: https://amzn.to/3DVqB8H Microphone mount: https://amzn.to/3BWUcOJ Monitors: https://amzn.to/3G2Jjgr Monitor mount: https://amzn.to/3AWGIAY Height-adjustable table: https://amzn.to/3aUysXC Ergonomic chair: https://amzn.to/3phQg7r PC case: https://amzn.to/3jdlI2Y GPU: https://amzn.to/3AWyzwy Keyboard: https://amzn.to/2XskWHP Bluelight filter glasses: https://amzn.to/3pj0fK2