---
title: "Neural network chip built using memristors"
description: "Paired memristors act like synapses to link circuitry that acts like neurons."
date: "2015-05-07"
modified: "2015-08-13"
authors:
  - name: "Ethan Fox"
    link: "https://futurism.com/authors/foxman"
url: "https://futurism.com/neural-network-chip-built-using-memristors"
categories:
  - "Science & Energy"
tags:
  - "computing"
---

# Neural network chip built using memristors

![Default Futurism featured image](<https://futurism.com/wp-content/uploads/2025/10/Futurism-Filler-Image.jpg>)

- Memristors have relatively simple behavior: they're a type of circuitry where the present resistance to current is a product of the currents that have flowed through them in the past. The more current that goes through, the easier it will travel through in the future.
- Memristors can be made of metal oxides. In this case, the authors used a combination of aluminum oxide and titanium dioxide (Al2O3 and TIO2) to form a memristor. The neural network was formed by linking traditional circuitry through a grid of wiring (technically a crossbar).
- The neural network was trained to identify three letters (V, N, and Z), including the possibility of single-pixel errors. After a single time through the training set, the network was able to successfully identify all three letters, although performance continued to improve with further experience.