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 22: Parallelising and distributing Deep Learning
Episode 21: Additional optimisation strategies for deep learning
Episode 20: How to master optimisation in deep learning
Episode 19: How to completely change your data analytics strategy with deep learning
Episode 18: Machines that learn like humans
Episode 17: Protecting privacy and confidentiality in data and communications
Episode 16: 2017 Predictions in Data Science
Episode 15: Statistical analysis of phenomena that smell like chaos
Episode 14: The minimum required by a data scientist
Episode 13: Data Science and Fraud Detection at iZettle
Episode 12: EU Regulations and the rise of Data Hijackers
Episode 11: Representative Subsets For Big Data Learning
Episode 10: History and applications of Deep Learning
Episode 9: Markov Chain Montecarlo with full conditionals
Episode 8: Frequentists and Bayesians
Episode 7: 30 min with data scientist Sebastian Raschka
Episode 6: How to be data scientist
Episode 5: Development and Testing Practices in Data Science
Episode 1: Predictions in Data Science for 2016
Episode 4: BigData on your desk
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