---
title: "Discussion on \"The loss curve never lies. Here is what backpropagation looks like when it learns.\" | Hashnode"
description: "Discussion on \"The loss curve never lies. Here is what backpropagation looks like when it learns.\". A beginner friendly walkthrough of the 1986 backpropagation paper by Rumelhart, Hinton and Williams. Plain words, clear diagrams, no PhD needed."
url: "https://hashnode.com/posts/backpropagation-loss-curve-gradient-visualization/69db46b1aadf1107e2a0eec4"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [The loss curve never lies. Here is what backpropagation looks like when it learns.](https://papersbyhand.hashnode.dev/backpropagation-loss-curve-gradient-visualization?utm_source=hashnode&utm_medium=feed)

A beginner friendly walkthrough of the 1986 backpropagation paper by Rumelhart, Hinton and Williams. Plain words, clear diagrams, no PhD needed.

Apr 3 · 3 min read · papersbyhand.hashnode.dev  
Read the article

-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#deeplearning](https://hashnode.com/tag/deeplearning)
-   [#begginers](https://hashnode.com/tag/begginers)
-   [#python](https://hashnode.com/tag/python)

## Written by

[Soham Kute](https://hashnode.com/@paperhand)

@paperhand · Mumbai, India

  
[View profile](https://hashnode.com/@paperhand)

building...

Day 3: I will add a loss curve, visualize the gradients in each layer, and push the full code to GitHub. You will see why gradients in early layers are much smaller than gradients in late layers. This matters for every deep model that exists.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
