From Ancient Greeks to Modern Geeks - Basic Machine Learning Algorithms
summary
Covers Naive Bayes, linear and logistic regression, k‑nearest neighbours and decision trees with concrete examples and code on GitHub, implemented in Excel using MMULT/TRANSPOSE and matrix inverse. Shows a Pokémon height→weight linear model with R² = 39.7% improved to 47.26% with multiple regressors, a correlation of 96.39% (Google profits vs cheese) to illustrate correlation ≠ causation, a logistic classifier reaching 98.88% accuracy on legendary Pokémon, and a k‑NN RGB colour classifier; all methods are demonstrated and evaluated.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 3:13Machine learning as Greek philosophy
- 5:19Cheating at Super Top Trumps
- 10:12Correlation in HP and Pokémon
- 13:38Linear regression for Pokémon weight
- 18:10Correlation vs causation
- 21:56Matrix operations for regression
- 24:48Logistic regression for legendary Pokémon
- 27:34Naive Bayes with Doctor Who
- 34:16K-nearest neighbors for colors
- 37:28Decision trees and Guess Who
- 43:13Recommended books
- 44:15Q&A
