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.
Episode 60: Predicting your mouse click (and a crash course in deeplearning)
Episode 59: How to fool a smart camera with deep learning
Episode 57: Neural networks with infinite layers
Episode 56: The graph network
Episode 55: Beyond deep learning
Episode 54: Reproducible machine learning
Episode 53: Estimating uncertainty with neural networks
Episode 52: why do machine learning models fail? [RB]
Episode 51: Decentralized machine learning in the data marketplace (part 2)
Episode 50: Decentralized machine learning in the data marketplace
Episode 49: The promises of Artificial Intelligence
Episode 48: Coffee, Machine Learning and Blockchain
Episode 47: Are you ready for AI winter? [Rebroadcast]
Episode 46: why do machine learning models fail? (Part 2)
Episode 45: why do machine learning models fail?
Episode 44: The predictive power of metadata
Episode 43: Applied Text Analysis with Python (interview with Rebecca Bilbro)
Episode 42: Attacking deep learning models (rebroadcast)
Episode 41: How can deep neural networks reason
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Lex Fridman Podcast