Machine Learning Explained to Humans
summary
Demonstrates concrete ML steps: implements linear and logistic regression with numpy, derives gradients and runs gradient descent to fit weights, shows inference as a one‑line ŷ = X·W, and trains a multiclass classifier on MNIST that reaches about 90.32% accuracy. Code is plain Python (~20 lines for the core), training is iterative and slower while inference is cheap, and the live demo briefly tripped but the scripts produce the reported model and results.
AI-written summary · about
chapters (8)
- 0:00Introduction to ML
- 1:08Linear regression basics
- 5:54Defining loss and error
- 12:23Gradient descent explained
- 19:10Training and inference
- 24:15Multivariate regression
- 38:11Logistic regression
- 42:37Computer vision application
related talks
33mMachine Learning explained to humans
44mMachine Learning Exposed
34mML from a software engineer's perspective
43mA Gentle Introduction to Neural Networks
44mMachine Learning: The Bare Math Behind Libraries
55mTensorflow: Learning Machines
51mMachine Learning Exposed Introduction to Machine Learning
45mFrom Ancient Greeks to Modern Geeks - Basic Machine Learning Algorithms