Hello EveryOne !!!

I am Abdulrehman working as Graduate Researcher in a University of Engineering and Technology, Lahore Pakistan. I have bee...

Hi guys,

I was wondering if any of you understand the step from 5.38 → 5.39 on page 123?

I thought the definition of Var[X] was simply:

P(y) = exp(y*z)/SUM[y'=0..1](y'*z) = exp(y*z)/(exp(0*z)+exp(1*z)) = exp(y*z)/(1+exp(z)) 6.22

P(y) = Sigmoid((2*y-1)*z) 6.23

where

Ya sure. In probablity theory, the sum of all possible outcomes sum over to 1. For example a coin(fair or not) can only land on two sides, heads and tails. So in neural networ if there are only two possible states 0 and 1 the probablity of them occuring add up to 1.

So if prob(1) is say X, the prob(0) would be 1-x.

Hello, Stefan! Welcome to the world of AI. If you are serious about learning machine learning and deep learning, I recommend you read Michael Nielsen's EBook "Neural Network and Deep Learning"...

Hi guys! I'm a 30 years old software engineer living in Japan.

Recently, I'm studying machine learning and deep learning for my product and investment for myself.

I'm using text book from Raschka and Udacity deep le...