Laboratory for Intelligent Probabilistic Systems

Ryan Adams

---

July 13, 2020

anemptytextlline

We often talk about the gradient of a scalar function as being the direction of steepest ascent. Rather than taking that for granted, let's convince ourselves that it is true. This is part of a series of videos for COS 302: Mathematics for Numerical Computation and Machine...

Ryan Adams

---

July 6, 2020

anemptytextlline

A useful way to think about derivatives (and gradients/Jacobians more generally) is as the maps that give you the best affine approximation at a point. This is part of a series of videos for COS 302: Mathematics for Numerical Computation and Machine Learning, replacing lectures after the course...

Ryan Adams

---

June 29, 2020

anemptytextlline

We think about gradients a lot in machine learning. This video talks about partial derivatives in general and Jacobian matrices, which specialize to gradients for scalar functions. This is part of a series of videos for COS 302: Mathematics for Numerical Computation and Machine Learning, replacing lectures...