# Tensorflow implementation

**URL:** <https://community.deeplearning.ai/t/tensorflow-implementation/297635>\
**Category:** Advanced Learning Algorithms\
**Tags:** week-module-1\
**Created:** [March 27, 2023, 4:40pm UTC](https://community.deeplearning.ai/t/tensorflow-implementation/297635 "2023-03-27T16:40:54Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Samy2705](https://avatars.discourse-cdn.com/v4/letter/s/34f0e0/32.png) [@Samy2705](https://community.deeplearning.ai/u/Samy2705)\
**Post date:** [March 27, 2023, 4:40pm UTC](https://community.deeplearning.ai/t/tensorflow-implementation/297635/1 "2023-03-27T16:40:54Z")

</div>

![neural](https://global.discourse-cdn.com/dlai/original/3X/6/4/64ef837e7fd33625083ca5247cea8dcbf0840a8e.png)

Can anybody help me understand what is those params and from where they came?  
and also this expression  
L1\_num\_params = 2 \* 3 + 3 # W1 parameters + b1 parameters  
L2\_num\_params = 3 \* 1 + 1 # W2 parameters + b2 parameters

I’m unable to understand from where they came and what do they signify?

---

<div class="post-metadata">

**Author:** ![ai\_curious](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/ai_curious/32/128003_2.png) [@ai\_curious](https://community.deeplearning.ai/u/ai_curious)\
**Post date:** [March 27, 2023, 6:51pm UTC](https://community.deeplearning.ai/t/tensorflow-implementation/297635/2 "2023-03-27T18:51:57Z")

</div>

It’s provided in the comment in the notebook. L1 params is the count of trainable parameters in the first layer, which has W\_1 of shape (2,3) and b\_1 shape (1,3). 2 is the number of inputs, 3 is the number of nodes. Similar idea for W\_2 and b\_2, but constrained by the shape of the previous layer (3) and the shape of the output (1).