h4unt010gy


« The figure of the ghost as that which is neither present, nor absent, neither dead nor alive »

repetitive music and learning machine

Explications par Damien Henry

I used videos recorded from trains windows, with landscapes that moves from right to left and trained a Machine Learning (ML) algorithm with it.

First, it learns how to predict the next frame of the videos, by analyzing examples. Then it produces a frame from a first picture, then another frame from the one just generated, etc. The output becomes the input of the next calculation step. So, excepting the first one that I chose, all the other frames were generated by the algorithm.

The results are low resolution, blurry, and not realistic most of the time. But it resonates with the feeling I have when I travel in a train. It means that the algorithm learned the patterns needed to create this feeling. Unlike classical computer generated content, these patterns are not chosen or written by a software engineer.
In this video, nobody made explicit that the foreground should move faster than the background: thanks to Machine Learning, the algorithm figured that itself. The algorithm can find patterns that a software engineer may haven’t noticed, and is able to reproduce them in a way that would be difficult or impossible to code.

What you see at the beginning is what the algorithm produce after very little learnings. It learns more and more during the video, that’s why there are more and more realistic details. Learnings is updated every 20s.

[table “4” not found /]

2k17•05