An algorithm imagines a train ride

57 minutes

Machine learning is important, but some AIs just want to have fun

Set to the pulsing, ethereal sounds of Steve Reich’s minimalist score Music for 18 Musicians (1974-6), this video by the French computer programmer Damien Henry is a clever visual demonstration of machine learning – a term coined by the US computer scientist Arthur Samuel (1901-1990) to describe an algorithm that gives computers the ‘ability to learn without being explicitly programmed’. 

Using several videos recorded from windows during train rides, Henry trained an algorithm to predict what the next frame of a train ride should look like. Then, starting with a single frame chosen by Henry, the algorithm generated, to the best of its ability, scenes from an hour-long train ride, improving itself roughly every 20 seconds. The resulting video demonstrates machine learning in action through a dreamy, impressionistic take on the experience of observing flowing, fleeting landscapes passing by. Though machine-learning algorithms are used more practically in applications where adaptability is greatly advantageous, such as anti-virus software and driverless cars, there’s an undeniable charm to seeing a computer engage in a version of one of our more ephemeral but corporeal experiences – the train ride.

Via Kottke.org

Director: Damien Henry

Music: Steve Reich

Get Aeon straight
to your inbox
Join our newsletter Sign up
Follow us on
Facebook
Like

‘Aeon is what readers and writers dream about. It is wide in scope, without ever being shallow. It offers stimulating issues, yet never seeking to be tantalising.

Publishing at its best. I love it.’

Professor Luciano Floridi, University of Oxford

‘Aeon is consistently the place to find excellent, provocative and thoughtful writing.

One of my favourite places to find new writers and new ideas.’

Professor Sophie Kerttu Scott, University College London

‘Aeon, for me, continues to be one of the best places to spend a quiet afternoon, in the company of some of the most brilliant minds around.’

Shivam C, India, Friend of Aeon

‘Every morning I look forward to seeing what’s in your email and there isn’t a day that goes by without reading or watching something you guys have published.

It’s like an oasis of sanity in a world gone mad.’

Jack D, USA, Friend of Aeon

‘Aeon is one of the liveliest, most wide-ranging and imaginative sources of good content on the web.

A fabulous resource for the intelligent and curious.’

Professor Barry C. Smith, University of London

Aeon is a registered charity committed to the spread of knowledge. Our mission is to create a sanctuary online for serious thinking.
But we can’t do it without you.

Aeon is a registered charity committed to the spread of knowledge and a cosmopolitan worldview.
But we can’t do it without you.

Support Aeon

Essay/
Future of Technology
Do platforms work?

The distributed network has gobbled the hierarchical firm. Only by seizing the platform can workers avoid digital serfdom

George Zarkadakis

Essay/
Future of Technology
Fuelling the future

Fantasies about new power sources for human ambitions go back a century or more. Could these past visions energise our own future?

Iwan Rhys Morus