---
title: "Neural Turing Machines"
description: "Neural Turing Machines give a neural controller a separate, mutable memory and make its read and write addresses differentiable. Read it to see how content lookup and relative shifts combine, why the copy trace looks like a learned algorithm, and where the paper's preliminary synthetic evidence stops."
canonical_url: "https://fanout.sh/daily/2026-10-22-neural-turing-machines"
md_url: "https://fanout.sh/daily/2026-10-22-neural-turing-machines.md"
last_updated: "2026-10-22"
access: "public"
---

# Neural Turing Machines

Neural Turing Machines give a neural controller a separate, mutable memory and make its read and write addresses differentiable. Read it to see how content lookup and relative shifts combine, why the copy trace looks like a learned algorithm, and where the paper's preliminary synthetic evidence stops.

## Paper details

- Authors: Alex Graves, Greg Wayne, and Ivo Danihelka

- Venue: arXiv 2014

- Track: AI Research

- Difficulty: Medium

- Reading time: 28 min

- Original paper: https://arxiv.org/abs/1410.5401v2

## What you will learn

- How a normalized weighting turns a discrete memory address into a trainable soft read or write.

- Why content addressing finds a matching row while location addressing iterates from the previous focus.

- What the copy memory trace establishes, and why fixed capacity and missing seed variation bound the claim.

## Continue exploring

[Start with soft attention](https://fanout.sh/daily/2026-09-16-neural-translation-soft-attention): Review how differentiable weights select information before applying the same idea to mutable external memory.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md