Видео

Yes, for example in the calculation of LSTM gates and gated recurrent units (GRUS) in deep learning

at 1:15

It is given. alpha lies between 0 and 0.5 and beta lies between 0 and 1.

The while condition is just there to let you know to continue the inequality (updating epsilon or t in some textbooks) until it no longer holds. Then your Xc will be the last value where the inequality did not longer hold. Evaluate your objective function at this Xc to mimimize it.

@@leotorres300 thanks for the reply! I understand the logic. But I just want to know math of this while condition. why exactly is in that form? is it from gradient or what? it cannot be any arbitrary condition

Thank you!

It was not made by a robot, but thanks 😂

easyupload.io/ujy6cq link will work for 7 days.

I'm glad it helped 😄

Thank you for watching! :)

Thank you for watching! :)

Both distributions can be used as a prior for Bayesian Inference. The probability of the failure of a battery over time can be modeled as exponential distribution. With time, the probability of a failure grows exponentially. Laplace distributions are encountered in finances, you can check the paper "Modelling and predicting market risk with Laplace-Gaussian mixture distributions".

Applied statistics and probablility for engineers 6th edition by Douglas Montgomery and George Runger chapter 7.4.2, example 7-13 may be what you're looking for, but I'm not sure.

Thank you sir i will check it God place you 🌸😍💐

Thank you for the question. In the example, the outcome of one coin does not affect the outcome of the other. As mentioned at 1:00 , the two events are independent, that is why when we calculate P(A=H|B=T) it equals P(A=H). If we had dependent events, it could have been the case that P(A=H|B=T) != P(A=H). Regardless of the dependency, it is true that P(A=H|B=T) = P(A=H, B=T)/P(B=T). The example showed how to use the formula.

@@deepshallownet5206 OK u should state that the experiment is independent

It really depends on what you goal is. This book gives less elaboration than the standalone books dedicated to the linear algebra. For example there are no exercises, which you will always find in the linear algebra books. It covers only the minimum, which is required to understand rest of the deep learning, but there still are some details in the book that may be hard to grasp at first. However after watching these videos, the book should be easier to understand. Also, this playlist omits the principal component analysis derived with just linear algebra. If you want to understand that part, you will have to read the chapter. Anyway, reading the book would not hurt. The book often skips the examples of concepts making them hard to understand. But these videos explain them in an easier way and provide examples.