Logistic regression with a Neural Network mindset (prepare data) part 4

Logistic regression is a binary classification method. In this full tutorial, after being trained on images of cats and dogs and then being given a picture that it has never seen before of a cat (y=0) or a dog (y=1), we will find out if the machine can predict the correct type. As we’ll see, even a simple algorithm like logistic regression can do this task surprisingly well.

In this tutorial we will build the general architecture of a learning algorithm, including parameter initialization, cost function, and gradient calculation, using an optimization algorithm (gradient descent). After that, we will gather all three functions above into the main model function, in the right order. All in all, we will not use loops (for/while) in your code, unless this will be necessary to do so, to maximize our code performance.

✅ Support My Channel Through Patreon:

✅ One-Time Contribution Through PayPal:

[ohmigawd]

Is it possible to get an explanation on the 26. line? I cannot understand the X[i, :] syntax at all