# Back propagation - computation graph

**URL:** <https://community.deeplearning.ai/t/back-propagation-computation-graph/395372>\
**Category:** Advanced Learning Algorithms\
**Tags:** week-module-2\
**Created:** [July 24, 2023, 12:03pm UTC](https://community.deeplearning.ai/t/back-propagation-computation-graph/395372 "2023-07-24T12:03:41Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Nathan\_Angell](https://avatars.discourse-cdn.com/v4/letter/n/77aa72/32.png) [@Nathan\_Angell](https://community.deeplearning.ai/u/Nathan_Angell)\
**Post date:** [July 24, 2023, 12:03pm UTC](https://community.deeplearning.ai/t/back-propagation-computation-graph/395372/1 "2023-07-24T12:03:41Z")

</div>

Hello,

I am looking at the computation graph video, which is located in the back propagation section, and I have a question on one of the slides that he presents. If you look at the image below, I was wondering how he was able to get 2 for the variable y. I thought to get this answer, it would be wx + b which is 4, not 2. I am most likely missing something and I would like to know what it is.

 ![image](https://global.discourse-cdn.com/dlai/original/3X/4/f/4f09dac6ef362ab35297e7a51603df11b85cc411.jpeg)

---

<div class="post-metadata">

**Author:** ![rmwkwok](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rmwkwok/32/126977_2.png) [@rmwkwok](https://community.deeplearning.ai/u/rmwkwok)\
**Post date:** [July 24, 2023, 12:09pm UTC](https://community.deeplearning.ai/t/back-propagation-computation-graph/395372/2 "2023-07-24T12:09:59Z")

</div>

Hello @Nathan_Angell,

Go to 1:15 of the video. y is the ground truth label, so it is given and not computed. In contrast, a is the prediction and is computed.

Cheers,  
Raymond

---

<div class="post-metadata">

**Author:** ![Nathan\_Angell](https://avatars.discourse-cdn.com/v4/letter/n/77aa72/32.png) [@Nathan\_Angell](https://community.deeplearning.ai/u/Nathan_Angell)\
**Post date:** [July 25, 2023, 11:41am UTC](https://community.deeplearning.ai/t/back-propagation-computation-graph/395372/3 "2023-07-25T11:41:19Z")

</div>

alright thank you!

---

<div class="post-metadata">

**Author:** ![lianghsun](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/lianghsun/32/10288_2.png) [@lianghsun](https://community.deeplearning.ai/u/lianghsun)\
**Post date:** [September 4, 2023, 5:06am UTC](https://community.deeplearning.ai/t/back-propagation-computation-graph/395372/4 "2023-09-04T05:06:47Z")

</div>

Hello community members 😀, I’d like to further ask about computation graphs based on this discussion.

The computation graphs in the course differs from what I’ve typically observed elsewhere. Referencing the attached image, does this suggest that there are varying approaches to depicting computation graphs, or do both representations convey the same concept? Thanks.

![](https://global.discourse-cdn.com/dlai/original/3X/3/d/3dfbed7f5152b2ca723791a068cc3e0630b683a7.jpeg)
