# Back Propagation

These notes are from the video series of [CampusX YouTube](https://www.youtube.com/@campusx-official)' playlist: [100 Days of Deep Learning](https://youtube.com/playlist?list=PLKnIA16_RmvYuZauWaPlRTC54KxSNLtNn\&si=ytwvd2InN9ECzXVX). I have just written these for myself and for others to refer in future.&#x20;

In this notes, we'll have a try to understand what is back propagation. You can find the first video of the series [here](https://youtu.be/6M1wWQmcUjQ?si=oOpHrJXlibxDZyYU).

Prerequisites:

* Forward propagation
* Gradient descent
* Notations: <https://youtu.be/H0_3SJh4Rqs?si=G6mu8dLpMmjcVt68>

Notes are divided into 2 parts:

* [What is back propagation?](/deep-learning/topic-wise-notes/back-propagation/what-is-back-propagation.md)
* [How does it work?](/deep-learning/topic-wise-notes/back-propagation/how-does-it-work.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://notes.adarshdubey.com/deep-learning/topic-wise-notes/back-propagation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
