HackerTube
HomeLongsLikedHistoryWatch laterCategoriesPlaylistsSettings

MENACE: the pile of matchboxes which can learn

Stand-up Maths2 HN recommenders · recommended in 2 months, 2018-2026
YouTube
453K views · 8 years ago · explainer · evergreen

Matt Parker of Stand-up Maths demonstrates MENACE, Donald Michie's 1961 machine made of matchboxes that learns to play noughts and crosses through reinforcement. He builds and trains a physical version.

HN cites it as a fun, tangible way to teach machine learning, including to kids.

Machine learning & deep learningRecreational & visual mathHistory of computing#menace#reinforcementlearning#tic-tac-toe#donaldmichie#mattparker#machinelearninghistory

5 comments from Hacker News

@Tachyooon2026 · in “Learning to Play Tic-Tac-Toe with Jax”

The first time I heard of it was in this Matt Parker video where he helped do this with a school-sized group of kids [0]. An "AI player" made of matchboxes, run by schoolkids, is a fantastically fun idea. [0] ▶ this video

RecommendsView on HN
@jerf2025 · in “Solving a Childhood Mystery: How BASIC Games Learned to Win”

Matt Parker did a video about a physical implementation of MENACE as part of a museum display for a day: ▶ this video

CitesView on HN
@Tachyooon2023 · in “A Matchbox Game-Learning Machine (1991) [pdf]”

Seems like this is what Matt Parker built together with some other people a few years ago: ▶ this video . It's incredibly inefficient compared to running it on a computer, but an amazing way to teach kids about this.

RecommendsView on HN
@jimktrains22023 · in “A Matchbox Game-Learning Machine (1991) [pdf]”

Stand up maths did an episode on a similar "machine" called MENACE (Machine Educable Noughts And Crosses Engine) that learns to play tick tac toe. ▶ this video The video description has additional links to resources: link link

RecommendsView on HN
@notEvenOnce2018 · in “On Intelligence in Cells: The Case for Whole Cell Biology (2009) [pdf]”

The concept fits. Consider MENACE (Machine Educable Noughts And Crosses Engine). ▶ this video If cells operate in a similar fashion, where adaptation to externalities encodes itself into a durable surface of arbitrary pockets, then we have a recipe for inert systems exhibiting variable degrees of behavior, which is capable of evolving over time. This doesn't solve for sentience, but it does solve for expressive adaptation to fit into complex, hostile environments.

CitesView on HN
Computer program that learns to play classic NES games16:18

Computer program that learns to play classic NES games

suckerpinch
2.2M views • 13 years ago
Training an unbeatable AI in Trackmania20:41

Training an unbeatable AI in Trackmania

Yosh
17.7M views • 3 years ago
The Unbeatable Game from the 60s: Dr NIM11:39

The Unbeatable Game from the 60s: Dr NIM

Stand-up Maths
7.2M views • 10 years ago
MarI/O - Machine Learning for Video Games5:58

MarI/O - Machine Learning for Video Games

SethBling
11.5M views • 11 years ago
Lecture 01 - The Learning Problem1:21:28

Lecture 01 - The Learning Problem

caltech
1.5M views • 14 years ago
Teaching Robots New Behaviors3:32

Teaching Robots New Behaviors

Toyota Research Institute
88K views • 3 years ago
Lecture 1 | Machine Learning (Stanford)1:08:40

Lecture 1 | Machine Learning (Stanford)

Stanford
2.7M views • 18 years ago
The Strange Math That Predicts (Almost) Anything32:32

The Strange Math That Predicts (Almost) Anything

Veritasium
13.1M views • 1 year ago
Math Encounters -- Five Balls, Two Hands: The Patterns of Juggling -- Colin Wright (Presentation)1:11:48

Math Encounters -- Five Balls, Two Hands: The Patterns of Juggling -- Colin Wright (Presentation)

National Museum of Mathematics
33K views • 14 years ago
OpenAI Plays Hide and Seek…and Breaks The Game! 🤖6:02

OpenAI Plays Hide and Seek…and Breaks The Game! 🤖

Two Minute Papers
11M views • 7 years ago
Infinite Mario AI - Long Level1:11

Infinite Mario AI - Long Level

Robin Baumgarten
1.3M views • 17 years ago
The Fastest Maze-Solving Competition On Earth25:22

The Fastest Maze-Solving Competition On Earth

Veritasium
25.3M views • 3 years ago
Clutching at Random Straws, Matt Parker | LMS Popular Lectures 20101:03:07

Clutching at Random Straws, Matt Parker | LMS Popular Lectures 2010

London Mathematical Society
601K views • 12 years ago
Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive1:05:25

Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive

GDC Festival of Gaming
35K views • 6 years ago
P vs. NP and the Computational Complexity Zoo10:44

P vs. NP and the Computational Complexity Zoo

hackerdashery
3.7M views • 12 years ago
The Day FPS Games Died8:28

The Day FPS Games Died

Basically Homeless
2M views • 5 years ago
Glitch Tokens - Computerphile19:29

Glitch Tokens - Computerphile

Computerphile
353K views • 3 years ago
Evolved Virtual Creatures (1994)4:09

Evolved Virtual Creatures (1994)

karlsims
43K views • 6 years ago
Deepmind artificial intelligence @ FDOT144:41

Deepmind artificial intelligence @ FDOT14

Elizr
288K views • 12 years ago
RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning1:28:13

RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning

Google DeepMind
1.9M views • 11 years ago