W3 Assignment error during training loop

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

In W3 assignment, during nn_model() phase. appears that my weights doesnt change per loop.

{moderator edit - solution code removed}

I have checked all functions. all of them passed their individual test. Non of them is zero in the loop as well. I assume there is something wrong about reassigning parameters in update_parameters function, some kind of pointer error etc.

{moderator edit - solution code removed}

is content of update_parameters(). What is the problem here? How do i solve this?
I got %75 percent already but I wanna understand my mistake.

2

If your update_parameters function passes the tests for it, then that is not where the problem is. The problem is that you are either not calling it correctly from nn_model or you are not correctly using the return values. E.g. check the variable names your using to call update_parameters and then handling the return values.

<Update>: You can see the bug in the code you showed:

paramaters is not the same as parameters, right?

Programming is a game of details: a single character wrong can ruin your whole afternoon. :nerd_face:

3

:smiley: Hahahah, it looks reaaly alike a and e. didnt even notice. Thanks for help. I was looking for algorithmic mistake for an hour. May be ı should just put it in VScode and see some basic mistakes with highlights :slight_smile:

1 Like