Lesson 06: A softer perceptron, part II: likelihood and loss #education #science #deeplearning

Hinzugefügt: 2026-05-18

[00:00:00]Overall, what was our objective here?

[00:00:02]This guy here is telling me the badness of my weight. Which kind of weight would we want for our model?

[00:00:11]The least bad weights, right? Finding the optimal weight.

[00:00:19]It's going to be argmin of this guy, right?

[00:00:25]Which we call W check. So, [clears throat] W check is the arg minimizer of our loss. How do I pay the least amount of cost for the red guys?

[00:00:37]Which of these 1 2 3 4 5 curves should I pick? Purple, right? The purple has the least amount of cost for my red guys.

[00:00:49]The largest my W1 and the sooner this purple will go down to zero at the after the crossing point, right?