Sign up to save your podcasts
Or
Share Episode 58: There is physics in deep learning!
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Episode 58: There is physics in deep learning!
There is a connection between gradient descent based optimizers and the dynamics of damped harmonic oscillators. What does that mean? We now have a better theory for optimization algorithms.
In this episode I explain how all this works.
All the formulas I mention in the episode can be found in the post The physics of optimization algorithms
Enjoy the show.
View all episodes
By Francesco Gadaleta
4.2
7272 ratings
There is a connection between gradient descent based optimizers and the dynamics of damped harmonic oscillators. What does that mean? We now have a better theory for optimization algorithms.
In this episode I explain how all this works.
All the formulas I mention in the episode can be found in the post The physics of optimization algorithms
Enjoy the show.
More shows like Data Science at Home
View all
Freakonomics Radio
31,983 Listeners
Global News Podcast
7,598 Listeners
WSJ Your Money Briefing
1,706 Listeners
The a16z Show
1,092 Listeners
Software Engineering Daily
622 Listeners
Talk Python To Me
584 Listeners
Science Magazine Podcast
823 Listeners
Super Data Science: ML & AI Podcast with Jon Krohn
302 Listeners
FT Tech Tonic
98 Listeners
Worklife with Adam Grant
9,156 Listeners
Practical AI
205 Listeners
Last Week in AI
306 Listeners
Hard Fork
5,509 Listeners
This Day in AI Podcast
228 Listeners
The Last Invention
1,107 Listeners