---
title: "Discussion on \"Grokking of MLP on Modular Addition\" | Hashnode"
description: "Discussion on \"Grokking of MLP on Modular Addition\". Background\nGrokking is a phenomenon where a model quickly achieves near-perfect training accuracy (memorization), while validation accuracy remains near chance (or even worse-than-chance) for a long time, and then later transitions sharply to strong ..."
url: "https://hashnode.com/posts/grokking-of-mlp-on-modular-addition/69751862c6c0290f8faee595"
---

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

Discussion

# [Grokking of MLP on Modular Addition](https://taot.hashnode.dev/grokking-of-mlp-on-modular-addition?utm_source=hashnode&utm_medium=feed)

Background Grokking is a phenomenon where a model quickly achieves near-perfect training accuracy (memorization), while validation accuracy remains near chance (or even worse-than-chance) for a long time, and then later transitions sharply to strong ...

Jan 24 · 4 min read · taot.hashnode.dev  
Updated Feb 8  
Read the article

-   [#grokking](https://hashnode.com/tag/grokking)
-   [#mlp](https://hashnode.com/tag/mlp)

## Written by

[Terry Tao](https://hashnode.com/@taot)

@taot

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

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
