YoVDO

Noether Networks - Meta-Learning Useful Conserved Quantities

Offered By: Yannic Kilcher via YouTube

Tags

Machine Learning Courses Deep Learning Courses Neural Networks Courses Model Optimization Courses Inductive Bias Courses

Course Description

Overview

Explore the concept of Noether Networks in this in-depth video featuring an interview with first author Ferran Alet. Delve into the innovative approach of using Noether's theorem to connect symmetries with conserved quantities, enabling the dynamic and approximate enforcement of symmetry properties in deep neural networks. Learn about the potential of automatically discovering useful symmetries to improve machine learning performance, with a focus on sequential prediction problems. Gain insights into the architecture of Noether Networks, the optimization of Noether Loss, and the framework for discovering inductive biases. Examine experimental results and engage in a thoughtful discussion on the implications and applications of this groundbreaking research in the field of deep learning and symmetry exploitation.

Syllabus

- Intro & Overview
- Interview Start
- Symmetry priors vs conserved quantities
- Example: Pendulum
- Noether Network Model Overview
- Optimizing the Noether Loss
- Is the computation graph stable?
- Increasing the inference time computation
- Why dynamically modify the model?
- Experimental Results & Discussion


Taught by

Yannic Kilcher

Related Courses

3D-печать для всех и каждого
Tomsk State University via Coursera
Developing a Multidimensional Data Model
Microsoft via edX
Launching into Machine Learning 日本語版
Google Cloud via Coursera
Art and Science of Machine Learning 日本語版
Google Cloud via Coursera
Launching into Machine Learning auf Deutsch
Google Cloud via Coursera