– [Narrator] Babies are adorable when they’re playing with toys, right? But as they play, babies are also learning how their bodies move and how to manipulate objects. Berkeley researchers took inspiration from what they call, babies motor babbling, and programmed that kind of learning into a robot. Meet Vestri.… Continue Reading Vestri the robot imagines how to perform tasks

OK. Good morning, everyone. This is Jack Van Horn from the BD2K Training Coordinating Center at the University of [? Southern ?] California. And I’d like to welcome you all to our [INAUDIBLE] Knowledge Guide to the Fundamentals of Data Science. Today we’re going to be hearing from Daniela Witten… Continue Reading Supervised Machine Learning

DANIELA RUS: So today, I want to tell you about some of the extraordinary things we are experiencing these days in both academia, business, and industry. So think about it. Today, doctors can connect with patients and teachers can connect with students that are thousands of miles away. We have… Continue Reading Impact of AI and Robotics: Advances and Aspirations | J.P. Morgan

Hi Michael!>>Hey Charles! How’s it going?>>It’s going pretty well. How’s it going with you?>>It is a beautiful fall day here in Providence Rhode Island.>>Oh that’s right it’s fall, when you are.>>[LAUGH] Yeah, I think, that’s right.>>So, what we’re going to do today, Michael. If you will indulge me. Is ,we’re… Continue Reading Instance Based Learning Before – Georgia Tech – Machine Learning

Although conditional entropy can tell us when two variables are completely independent, it is not an adequate measure of dependence. Now consider the conditional entropy of y given the variable x. This conditional entropy may be small if x tells us a great deal about y or that x of… Continue Reading Mutual Information – Georgia Tech – Machine Learning

All right. So that’s supervised learning and unsupervised learning. That’s pretty good. The last one is reinforcement learning.>>[SOUND].>>Now reinforcement learning is what we both do, so Michael does a little bit of reinforcement learning here and there. You’ve got how many papers published in reinforcement learning?>>All of them. [LAUGH] Several.… Continue Reading Reinforcement Learning – Georgia Tech – Machine Learning

>>Okay, so, let me give you just a few more examples, Michael, of a, how PCA and ICA differ. And I’m going to do this mainly by talking about certain things that ICA does. And this is really just for your edification, but I think it really helps, to think… Continue Reading PCA vs ICA Continued – Georgia Tech – Machine Learning

So it is important to get an example I, I think that the, the best way to kind of see an example here is to draw a little picture for you that tells you what the sort of underlying assumption behind ICA is. So here’s the kind of, or at… Continue Reading Independent Components Analysis Two – Georgia Tech – Machine Learning

Speaking of solutions, this is the last little bit of thing that you need to know. And that is. This defines a problem. But, what we also want to have, whenever we have a problem. Is a solution. So, the solution to the Markov Decision Process, is something called a… Continue Reading Markov Decision Processes Four – Georgia Tech – Machine Learning

>>Okay, so, inspired by 20 questions let’s try to write down exactly what it is that you did in going through your 20 questions to get your answer to discover Michael Jackson was the person I was thinking about. So, what is the very first thing you did?>>I tried to… Continue Reading Decision Trees Learning – Georgia Tech – Machine Learning