Cross-Entropy Loss Log-likelihood Perspective

This is a video that covers Cross-Entropy Loss Log-likelihood Perspective
Attribution-NonCommercial-ShareAlike CC BY-NC-SA
Authors: Matthew Yedlin, Mohammad Jafari
Department of Computer and Electrical Engineering, University of British Columbia.

[@victorialeigh2726]

I really like that you guys hand clean the clear board. Feels like back in the classroom + math teather's small math talk!

[@vaibhavarora9408]

Great lectures. Thank you Matt Yedlin.

[@yanbowang4020]

love your video hope to see more of it.

[@yjy8]

you just cleared my doubt about likelihooh and log likelihood which I had for past yaer and half.
Thank you so much

[@GenerativeDiffusionModel_AI_ML]

Well explained using human language.

[@davidlearnforus]

Hi, thank you so much! I am self lerner, with no much of formal background. Can you please explain how SUM p_i log q_i is entropy, because it does not have minus sign. If it would be log (1/q_i) we would get minus sign out of it but its not. I'm stuck there...

[@AChadi-ug9pg]

Muhammad is a good student

[@GenerativeDiffusionModel_AI_ML]

I want to know how you can write on the mirror and record it.

[@mattyedlin7292]

The camera sees the writing flipped through a mirror.

[@TylerMatthewHarris]

thanks!

[@peizhiyan2916]

Nice

[@jimbobur]

*(EDIT: Solved it, see comment reply)*
I don't follow how you go from the case of numerical example, where the likelihood is a product of predicted and observed probabilities p_i and q_i each raised to the number of times they occur, to the algebraic expression of the likelihood where you take the product of q_i raised to N * p_i (or is that N_p_i? I'm a little unsure if the p_i is a subscript of the N or multiplied by it).

[@jimbobur]

I worked it out. The answer is to remember that the number of times the outcome i, with probability p_i occurs can be expressed by rearranging the definition p_i = N_p_i / N and substituting this into the expression for the likelihood in the general form that follows from the numerical example:
L = Π q_i ^ N_p_i ,
giving
L = Π q_i ^ N*p_i

[@garrettosborne4364]

Can the old guy.