Creator
Covers: theory of Machine Learning in Physics
Estimated time needed to finish: 10 minutes
Questions this item addresses:
  • How do you teach physics to machine learning models?
How to use this item?

This resource describes machine learning, physics-based models, and a hybrid of both. It is a great starting point to understanding how you can transition from traditional physics models to data-driven ML models.

Author(s) / creator(s) / reference(s)
By Vegard Flovik, Lead Data Scientist at Axbit AS
0 comment
Recipe
publicShare
Star(0)

Machine Learning In Physics

Contributors
Total time needed: ~2 hours
Objectives
This recipe introduces Machine Learning in Physics. It describes the motive for applying ML in physics, and discusses current progress and challenges in the field with detail.
Potential Use Cases
Incorporating physics into ML models, Using ML models to learn physics
Who is This For ?
INTERMEDIATEPhysics researchers, machine learning engineers incorporating physics
Click on each of the following annotated items to see details.
Resources3/7
ARTICLE 1. Introduction to Machine Learning for Physics
  • How do you teach physics to machine learning models?
10 minutes
PAPER 2. ML in Physics and the Physics of Learning
  • What are the challenges of applying ML to Physics? How can ML Models leverage physical laws? What kind of models are used for each physics problem?
30 minutes
VIDEO 3. Application of ML in Fluid Dynamics
  • How can we use ML to solve a physics problem: turbulence modelling?
20 minutes
ARTICLE 4. Algorithm for backpropagation
  • Pseudocode for Back Propagation
20 minutes
VIDEO 5. Intuitive understanding of Backward Propagation
  • What is Forward Propagation?
  • What is Backward Propagation?
10 minutes
OTHER 6. Convolutional Neural Network
  • What is a convolutional neural network?
10 minutes
BOOK_CHAPTER 7. Encoder-Decoder network explained
  • What is encoder- decoder network ?
30 minutes

Concepts Covered

0 comment