Become an ML Developer
From zero programming to training and evaluating real models.
10 lessons, in order
The route
Read these top to bottom. Nothing here assumes knowledge you have not been given earlier in the list.
-
Python for AI
Python basics
Python is a way of writing step-by-step instructions for a computer using words close to English. It is the language almost all AI is built in.
-
Python for AI
NumPy
NumPy lets you do one operation to millions of numbers at once instead of one at a time. It is the foundation every AI library in Python is built on.
-
Python for AI
Pandas
Pandas is a table with named columns that you can filter, group and summarise in one line. It is where almost every AI project starts, because real…
-
Mathematics for AI
Statistics
Statistics is how you judge a whole pot from one spoonful. Your test set is that spoonful, which is why a benchmark number needs an error bar.
-
Machine Learning
What is machine learning?
Machine learning is how a computer works out a rule by looking at examples, instead of being handed the rule by a programmer.
-
Machine Learning
Linear regression
Linear regression draws the straight line that fits your data best, and uses it to predict a number for inputs it has never seen.
-
Machine Learning
Classification
Classification is sorting things into named groups decided in advance, and every classifier is really an argument about where to draw the boundary…
-
Machine Learning
Model evaluation
Model evaluation is measuring whether a trained model is actually any good, using scores that reveal its real mistakes instead of hiding them.
-
Machine Learning
Decision trees
A decision tree asks a series of yes-or-no questions, each one chosen to tidy the data into cleaner piles, until every branch ends in an answer you…
-
Machine Learning
Random forest
A random forest grows hundreds of deliberately different decision trees and lets them vote, turning the twitchiness of a single tree into a steadier…
When you finish
Build something with it. Reading alone will not make it stick — the first time you debug your own model is the moment it becomes real. Try the projects, and keep the error database open in another tab.