Bayes is BAE
summary
Explains that Bayes’ idea actually lets two noisy estimates combine into a more accurate one and shows working Kalman Filter examples: a chasing robot and a noisy plane-landing simulation that converge, plus discussion of extended/unscented Kalman variants for non‑linear motion. Walks through the coin puzzle (1913 Liberty Head nickel worth $3.7M, posterior 1/3 then 1/5 after two heads), provides Python implementation links, Udacity/GeorgiaTech course refs, and practical code to reproduce results.
AI-written summary · about
chapters (10)
- 0:00Introduction to prediction
- 1:22The legacy of Thomas Bayes
- 4:11Understanding Bayes rule
- 5:35Speaker background and tech
- 8:22The issue of gerrymandering
- 10:52Robotics and Kalman filters
- 15:55Math behind the probability
- 26:21Implementing the filter
- 34:06Advanced filtering concepts
- 36:40Conclusion and resources
related talks
44mBayes' Theorem: The Formula That Changed the World
31mGetting Started with Bayes in Engineering: Implementing Kalman Filters with RxInfer.jl
42mBayes and Bool Walk into a Bar
42mBayesDB: Query the Probable Implications of Data
25mScaling Bayesian Experimentation
42mProbably
43mHow to look like a statistician (...)
01h 28mBayesian Decision Analysis [Tutorial]