# Batch and Layer Normalization

**URL:** <https://community.pinecone.io/t/batch-and-layer-normalization/427>\
**Category:** General\
**Created:** [July 21, 2022, 12:29pm UTC](https://community.pinecone.io/t/batch-and-layer-normalization/427 "2022-07-21T12:29:02Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![discobot](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/discobot/32/2_2.png) [@discobot](https://community.pinecone.io/u/discobot)\
**Post date:** [July 21, 2022, 12:29pm UTC](https://community.pinecone.io/t/batch-and-layer-normalization/427/1 "2022-07-21T12:29:02Z")

</div>

Recent advances in deep learning research have revolutionized fields like medical imaging, machine vision, and [natural language processing](https://www.pinecone.io/learn/nlp/). However, it’s still challenging for data scientists to choose the optimal model architecture and to tune hyperparameters for best results.

* * *
This is a companion discussion topic for the original entry at [https://www.pinecone.io/learn/batch-layer-normalization/](https://www.pinecone.io/learn/batch-layer-normalization/)

---

<div class="post-metadata">

**Author:** ![kevinschmiedlin](https://avatars.discourse-cdn.com/v4/letter/k/df788c/32.png) [@kevinschmiedlin](https://community.pinecone.io/u/kevinschmiedlin)\
**Post date:** [February 24, 2023, 10:59am UTC](https://community.pinecone.io/t/batch-and-layer-normalization/427/2 "2023-02-24T10:59:11Z")

</div>

Hi, just wanted to note that in general Standardization does not transform input values such that they follow a normal distribution, as it is just a linear transformation.

---

<div class="post-metadata">

**Author:** ![Bala](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/bala/32/125_2.png) [@Bala](https://community.pinecone.io/u/Bala)\
**Post date:** [March 16, 2023, 1:09pm UTC](https://community.pinecone.io/t/batch-and-layer-normalization/427/3 "2023-03-16T13:09:47Z")

</div>

Hi, thank you for pointing out. I realize that I haven’t made assumptions on the input distribution to state it that way. The post has been updated for clarity.