2.7M views · Mar 30, 2016 · 6:53 · 6 HN recommenders · 6 mentions · discussed 2016–2017
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 Hacker News points people here: 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 comment, 2016
“This series by Josh Grodin got started recently and looks promising.”
Promising beginner machine learning video series.
This series by Josh Grodin got started recently and looks promising. I assume they will eventually cover neural network / deep learning basics. Hello World - Machine Learning Recipes #1 this video Visualizing a Decision Tree - Machine Learning Recipes #2 link
“2. Write basic Machine Learning code”
Step for writing basic machine learning code.
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 a noob you MUST learn the prerequisites. Follow these steps in order and I guarantee you will be competent with AI in six months tops.(from my past experience) - 1. Know what AI actually is link - 2. Write basic Machine Learning code this video - 3. Understand the Mathmatics involved link - 4. Get some important concepts, link - 5. Finnish off. link
“you'll be able to do cool stuff with machine learning.”
Accessible Google series for getting started with machine learning.
Honestly, it doesn't seem that complicated. Just watch this educational video series this video by Google, and you'll be able to do cool stuff with machine learning.
“scikit-learn is a better way to get started with machine learning.”
Scikit-learn based intro to machine learning.
I'd say scikit-learn is a better way to get started with machine learning. Check this out, for example: this video
“Very approachable! The first lesson is a classifier to separate apples and oranges.”
Approachable intro building an apples vs oranges classifier.
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. this video
“Machine Learning Recipes from Josh Gordon at Google”
Video series to take a beginner into ML.
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 videos on YouTube, then he could dive into ML/AI with: Machine Learning Recipes from Josh Gordon at Google this video Siraj Raval's channel on ML/AI/Programming link All that said, if you reallllly want a book: "Learn Python the hard way" by Zed Shaw link
