AI Hints
Statistics & Math for ML · Lesson 1 of 138

Why Statistics for ML?

The language of data.

⏱ 2 min read▶ Video at 0:00🎓 Free
Watch this lesson in the Statistics & Math for ML courseWatch on YouTube ↗Full Statistics & Math for ML course

Machine learning is learning from data. And statistics is the science of learning from data. So every model you'll ever train is built on a few simple ideas from statistics and math. In this course, we'll learn them one easy step at a time, with real Python code.

Why Statistics for ML?
From the video: Why Statistics for ML?
  • Machine learning learns from data
  • Statistics is the science of data
  • Simple ideas, real code

What we will cover

We'll start with describing data, averages and spread. Then probability, the maths of chance. Then distributions, like the famous bell curve. Then testing ideas with data. And finally, the math inside machine learning. Vectors, matrices, gradients, and loss functions.

Describing dataaverages and spread
Probabilitythe maths of chance
Inferencetesting ideas
ML mathvectors, gradients, loss

No scary formulas

You don't need to be good at math to follow this course. Every formula is explained in plain words first, and then we compute it in Python, so you can see the real numbers. If you can add, multiply, and write a little Python, you're ready.

keyvalue
Plain wordsbefore every formula
Pythoncomputes it for us
Real numberssee what happens
You needbasic Python

Summary

Statistics is how we learn from data, and it's the foundation of machine learning. Next, what data actually looks like.

Key takeaways
  • Stats is learning from data
  • ML is built on it
  • Code makes it concrete
Next up: Data and Variables — rows and columns