Can a physical stack of matchboxes learn to master a game of noughts and crosses?
In short: This video examines MENACE, a machine learning system built from matchboxes. It demonstrates how a simple physical contraption can be trained to play noughts and crosses, offering a tangible look at the origins of game-learning algorithms.
MENACE, which stands for Matchbox Educable Noughts and Crosses Engine, is a mechanical system designed to learn through experience. It was originally described in Donald Michie’s 1961 paper, Experiments on the mechanization of game-learning.
The system functions as an early example of artificial intelligence, where physical matchboxes act as the memory and decision-making components for playing the game. By observing how these boxes are used, one can understand the foundational concepts of how machines improve their performance over time.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: MENACE: the pile of matchboxes which can learn
To cite this card, link to https://intellectplus.co.uk/app/science-menace-the-pile-of-matchboxes-which-can-learn.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics