Hello World - Machine Learning Recipes #1
Google for Developers6 HN recommenders · 2016–2017
2.7M views · tutorial · dated · Uploaded 2016-03-30
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.
HN commenters recommend it as an approachable first step into machine learning for programmers, with an apples-vs-oranges classifier.
53:22Ruby Conf 12 - Y Not- Adventures in Functional Programming by Jim Weirich
Confreaks
2:25:52The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
49:55How Python was Shaped by leaky Internals, Armin Ronacher, Flask framework
Видео с мероприятий {speach!
38:47RailsConf 2014 - All the Little Things by Sandi Metz
Confreaks
26:53What the heck is the event loop anyway? | Philip Roberts | JSConf EU
JSConf
18:40But what is a neural network? | Deep learning chapter 1
3Blue1Brown
1:00:19How To Design A Good API and Why it Matters
Google TechTalks
10:13The Problem with Time & Timezones - Computerphile
Computerphile
6 comments from Hacker News
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 [VIDEO] Visualizing a Decision Tree - Machine Learning Recipes #2 [LINK]
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 [VIDEO] - 3. Understand the Mathmatics involved [LINK] - 4. Get some important concepts, [LINK] - 5. Finnish off. [LINK]
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.
I'd say scikit-learn is a better way to get started with machine learning. Check this out, for example: [VIDEO]
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]
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 [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]