Machine Learning explained to humans
summary
Concrete example: a Python script using numpy and plotting libraries implements linear regression to predict pizzas sold from reservations, computes mean squared error, and optimizes weight and bias with gradient descent (iterative updates, learning rate alpha). The demo prints loss per iteration and returns w≈1.2, b≈12, giving ~40.23 pizzas for 25 reservations. Code is a few dozen lines and runs in seconds; scaling to images needs millions of parameters and GPU-backed training.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:05Why Machine Learning
- 3:12Example
- 4:04Import Data
- 6:02Linear Regression
- 11:34Loss
- 14:02Mean Squared Error
- 19:28Math
- 21:26Gradient Descent
- 21:50Find Best Line
related talks
51mMachine Learning Explained to Humans
44mMachine Learning: The Bare Math Behind Libraries
51mMachine Learning Exposed Introduction to Machine Learning
54mMachine Learning explained with Examples
45mFrom Ancient Greeks to Modern Geeks - Basic Machine Learning Algorithms
48mLearning Machine Learning
27mDemystifying Machine Learning
22mReal-world applications of machine learning: Beyond the hype