MTH 448/563 Data-Oriented Computing

Fall 2018

Day 22 = Day -8, Thursday, Nov 8

The dark side

Chinese tech IDs people by how they walk

a neural network for object classification, cont'd

Supplementary reference: CS231n, a superb course from Stanford. Example lecture

class scores

the goal


a good starting point?

a "loss" function


Exercise: Compute the partial derivatives of the softmax function, expressing your answers in as simple a form as possible.

cross entropy

total loss

minimizing loss

loss landscape

20170530_154521.jpg 20170530_154018.jpg

gradient descent

The negative of the gradient of the loss points in the direction of steepest decrease: step that way.

Exercise: Use Inkscape or other program to draw a path of gradient descent from the tip of the arrow on this topographic map


Upload your edited image to UBlearns when you are done.

computing the gradient

(to be continued, using back-propagation on the computational graph)


try to disfavor crazy weights that do well on training but not on anything else

polynomial-fitting analogy

LeafSnap quiz


I will write more.