A Resource for Machine Learning

Metacademy is a community-driven, open-source platform for experts to collaboratively construct a web of knowledge. Right now, Metacademy focuses on machine learning and probabilistic AI, because that’s what the current contributors are experts in. But eventually, Metacademy will cover a much wider breadth of knowledge, e.g. mathematics, engineering, music, medicine, computer science…

Current focus is on machine learning and probabilistic AI.

Metacademy could not exist without a large amount of high quality learning resources, so the true credit goes to these experts. Nevertheless, Roger Grosse and Colorado Reed built this site and organized roughly 350 machine learning and probabilistic AI concepts that comprise the intellectual seed that will allow Metacademy to flourish into a globally accessible and understandable learning experience.

You can find more about the concepts related to the topic of Machines Learning in this Concept List

LinkLog: Deep Learning and the Google Brain

From The Man Behind the Google Brain

With Deep Learning, Ng says, you just give the system a lot of data “so it can discover by itself what some of the concepts in the world are.” Last year, one of his algorithms taught itself torecognize cats after scanning millions of images on the internet. The algorithm didn’t know the word “cat” — Ng had to supply that — but over time, it learned to identify the furry creatures we know as cats, all on its own.

This approach is inspired by how scientists believe that humans learn. As babies, we watch our environments and start to understand the structure of objects we encounter, but until a parent tells us what it is, we can’t put a name to it.