Video by freeCodeCamp.org · taught by Kylie Ying · streamed from YouTube. All rights remain with the creator.
Lesson 1: Machine Learning for Everybody
About this lesson
This beginner course by Kylie Ying introduces machine learning without assuming any previous experience, working in Google Colab notebooks so that nothing needs installing. It opens with how to load a real dataset into a notebook and then explains what machine learning is, how it relates to artificial intelligence and data science, and the difference between supervised and unsupervised learning. You learn what features are, how classification differs from regression, what it means to train a model and how data is prepared and split before training. The heart of the course is a sequence of classification algorithms, each explained in theory and then implemented on the same dataset: k-nearest neighbours, Naive Bayes, logistic regression and support vector machines. Neural networks come next, introduced conceptually and then built with TensorFlow as a classifier, so the results can be compared with the earlier models. The course then turns to regression, first with linear regression in theory and code, then by fitting the same problem with a single neuron and finally with a larger regression network in TensorFlow. The last part covers unsupervised learning, explaining k-means clustering and principal component analysis and implementing both on a new dataset. Throughout, the emphasis is on intuition and working code rather than heavy mathematics. Afterwards, read Chapter 1 of the course book, which works a nearest-neighbour vote and a set of metrics by hand.