Hello World - Machine Learning Recipes #1

Channel:Google for Developers · Length:6:52 · Published:2016-03-30 · Views:2690939

Watch on YouTube

Summary

The first episode of Google's Machine Learning Recipes series. It introduces machine learning and builds a first supervised-learning classifier in about six lines of Python using scikit-learn.

Why HN recommends it

HN commenters recommend it as an approachable first step into machine learning for programmers, with an apples-vs-oranges classifier.

Very approachable! The first lesson is a classifier to separate apples and oranges. — HN, 2016

Python, Ruby & scripting languages · Machine learning & deep learning

Subtitles (excerpt)

[MUSIC PLAYING] Six lines of code is all it takes to write your first Machine Learning program. My name's Josh Gordon, and today I'll walk you through writing Hello World for Machine learning. In the first few episodes of the series, we'll teach you how to get started with Machine Learning from scratch. To do that, we'll work with two open source libraries, scikit-learn and TensorFlow. We'll see scikit in action in a minute. But first, let's talk quickly about what Machine Learning is and why it's important. You can think of Machine Learning as a subfield of artificial intelligence. Early AI programs typically excelled at just one thing. For example, Deep Blue could play chess at a championship level, but that's all it could do. Today we want to write one program that can solve many problems without needing to be rewritten. AlphaGo is a great example of that. As we speak, it's competing in the World Go Championship. But similar software can also learn to play Atari games. Machine Learning is what makes that possible. It's the study of algorithms that learn from examples and experience instead of relying on hard-coded rules. So that's the state-of-the-art. But here's a much simpler example we'll start coding up today.

On Hacker News

Why book? I don't know about you or your cousin, but learning from a book is so slow and dry. Why not a video series or online tutorial? Hell, maybe teach him the basics and build a small project with him. Codecademy is a great way to learn a bit of syntax and then build something. 'How to make a website' is a good intro course for getting into web dev. There's also a lot of good python basic vid… — goldenbeet, 2017-05
I'd say scikit-learn is a better way to get started with machine learning. Check this out, for example: [VIDEO] — iverjo, 2016-10
You could watch the 'Hello World' Machine Learning Recipes videos by Josh Gordon at Google. Very approachable! The first lesson is a classifier to separate apples and oranges. [VIDEO] — kbaker, 2016-10
Honestly, it doesn't seem that complicated. Just watch this educational video series [VIDEO] by Google, and you'll be able to do cool stuff with machine learning. — mliker, 2016-09
Hello, my background is just like yours. Assuming you are a total noob I learned that AI is not like programming, where anyone with basic knowledge of computation can dive in. You can NOT just learn AI by reading other people's code. Its like Physics, there are solid principles you need to understand before you get in. The point: AI does not come with the "batteries included". If you are in deed … — max_, 2016-06

Related videos