# Are gamma and beta just for removing extra 1/(epsilon)^(½) when mu and sigma all equal zero? I don’t get why use z tilde in Andrew’s deep learning course?

**URL:** <https://deeptalk.lambda.ai/t/are-gamma-and-beta-just-for-removing-extra-1-epsilon-when-mu-and-sigma-all-equal-zero-i-don-t-get-why-use-z-tilde-in-andrew-s-deep-learning-course/1840>\
**Category:** Deep Learning: General Discussion\
**Created:** [August 28, 2020, 4:02pm UTC](https://deeptalk.lambda.ai/t/are-gamma-and-beta-just-for-removing-extra-1-epsilon-when-mu-and-sigma-all-equal-zero-i-don-t-get-why-use-z-tilde-in-andrew-s-deep-learning-course/1840 "2020-08-28T16:02:47Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![jacksonsteel](https://avatars.discourse-cdn.com/v4/letter/j/c77e96/32.png) [@jacksonsteel](https://deeptalk.lambda.ai/u/jacksonsteel)\
**Post date:** [August 28, 2020, 4:02pm UTC](https://deeptalk.lambda.ai/t/are-gamma-and-beta-just-for-removing-extra-1-epsilon-when-mu-and-sigma-all-equal-zero-i-don-t-get-why-use-z-tilde-in-andrew-s-deep-learning-course/1840/1 "2020-08-28T16:02:47Z")

</div>

> **[Normalizing Activations in a Network - Hyperparameter Tuning, Batch...](https://www.coursera.org/lecture/deep-neural-network/normalizing-activations-in-a-network-4ptp2)**
>
> Video created by DeepLearning.AI for the course "Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization". Explore TensorFlow, a deep learning framework that allows you to build neural networks quickly and easily, ...

![image](https://sea1.discourse-cdn.com/flex019/images/transparent.png)

---

_[View the full topic](https://deeptalk.lambda.ai/t/are-gamma-and-beta-just-for-removing-extra-1-epsilon-when-mu-and-sigma-all-equal-zero-i-don-t-get-why-use-z-tilde-in-andrew-s-deep-learning-course/1840)._