Get curated editors’ picks, peeks behind the scenes, film recommendations and more.
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.
Director: Damien Henry
Information and communication
There are many ways to make a flat map of the world – each of them a unique distortion
Liquid experiments show how beautiful things can happen when chemicals meet
What is it like to clean the world for tomorrow while the rest of a city sleeps?
Philosophy of mind
Caring for the vulnerable opens gateways to our richest, deepest brain states
The nearly forgotten origin myth of Hawaii’s third-gender healers, as told by one
A whirlwind tour of Hong Kong’s high-rises is an awesome meditation on urbanity
The Standard Model might be the most successful theory in science. But what is it?
An artist grapples with the loss of his brother, and the problem of canine abduction
Sports and games
After a day’s toil in California’s fields, labourers let loose in street races