# Planar Data Classification with One Hidden Layer, Programming Assignment, Week3

**URL:** <https://community.deeplearning.ai/t/planar-data-classification-with-one-hidden-layer-programming-assignment-week3/616734>\
**Category:** Neural Networks and Deep Learning\
**Tags:** week-module-3, coursera-platform\
**Created:** [April 25, 2024, 8:42pm UTC](https://community.deeplearning.ai/t/planar-data-classification-with-one-hidden-layer-programming-assignment-week3/616734 "2024-04-25T20:42:30Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Harshawardhan\_Deshpa](https://avatars.discourse-cdn.com/v4/letter/h/9d8465/32.png) [@Harshawardhan\_Deshpa](https://community.deeplearning.ai/u/Harshawardhan_Deshpa)\
**Post date:** [April 25, 2024, 8:42pm UTC](https://community.deeplearning.ai/t/planar-data-classification-with-one-hidden-layer-programming-assignment-week3/616734/1 "2024-04-25T20:42:30Z")

</div>

Exercise 6 : Question about backward\_propagation:

I took a look in the test dataset. Shape of X is (2,3) so two features and three examples.

Shape of W1 is (4,2). I take this to mean that we have four neurons. However, for the life of me I cant see where have we defined that the number of neurons is 4 ☹ Or is it that the number of neurons is the number of rows in W1?

Asking since in exercise 2 we explicitely define layer\_size n\_h = 4

---

<div class="post-metadata">

**Author:** ![paulinpaloalto](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/paulinpaloalto/32/187_2.png) [@paulinpaloalto](https://community.deeplearning.ai/u/paulinpaloalto)\
**Post date:** [April 25, 2024, 8:57pm UTC](https://community.deeplearning.ai/t/planar-data-classification-with-one-hidden-layer-programming-assignment-week3/616734/2 "2024-04-25T20:57:13Z")

</div>

Note that the test cases here don’t have to agree with the “real” dimensions we use in the final model we build. The test case is “self contained”: they just give you the parameters, which includes all the W and b values. So as you say, the shapes are what they are and you can deduce the number of neurons in each layer from that.
