Yahoo News Facebook wants to teach you all about how AI works
Pay attention, everyone: Facebook is trying to teach you something.
Since you probably let the social network distract you from just about every other educational opportunity that comes your way, you should at least learn a bit now.
SEE ALSO: Facebook to roomful of journalists: 'We hear you'
It's all about artificial intelligence. The already pervasive tech, according to a Facebook blog post, "remains mysterious" for most people even as they use AI systems every day.
The post was co-authored by Yann LeCun, head of Facebook's AI Research, and Joaquin Quiñonero Candela, who leads its Applied Machine Learning research division.
But don't worry if the thought of reading a long, dry block of jargon-filled text is keeping you from diving into the AI conversation — like everything else on Facebook, there's video. Six of them, to be exact.
The short clips, which a Facebook rep called "pretty much AI 101 to the community" in an email to Mashable, walk the viewer along the basic steps of a simple AI system. From machine learning to neural nets, they cover the basics to bring you up to speed
But since six videos might be a big ask for some people — even with Facebook's top minds sharing their peerless expertise — we watched them all to give you a quick takeaway. After all, smart machines are going to be the ones focused on learning in the future.
Introduction to AI
Takeaway: AI is EVERYWHERE. Machines take forever to start learning but adjust quickly once they have the hang of it.
Machine Learning
Takeaway: Algorithms are simple, repeatable processes — except when they're not. Weighted sums make it all work out.
Gradient Descent
Takeaway: A learning machine has its proverbial nobs twiddled by algorithms. The trial-and-error process to find the right level of fiddling is called gradient descent
Deep Learning
Takeaway: Learning machines are "deep" with layers of processing. The number of layers determines the depth of the system.
Back Propagation
Takeaway: The best way to find the the gradient of the output error is to go backwards. Also, calculus.
Convolutional Neural Nets
Takeaway: The convolutional network is the way nodes of the neural net connect — like our brains! By focusing on smaller parts, machines can recognize learned information in different contexts.
