01 machine learning Neural Networks

01 machine learning Neural Networks

Experiments with style transfer [2015]

Style transfer is the technique of recomposing images in the style of other images. These were mostly created using Justin Johnson’s code based on the paper by Gatys, Ecker, and Bethgedemonstrating a method for restyling images using convolutional neural networks. Instructions here, and more details here. A gallery with all of these and more style transfers can be viewed here.

 

http://genekogan.com/works/style-transfer/

 

 

 

World’s Tiniest Violin

Created by Design I/O, World’s Tiniest Violin is a ‘speed project’ that uses Google’s Project Soli – Alpha Dev Kit combined with the Wekinator machine learning tool and openFrameworks to detect small movements that look like someone playing a tiny violin and translate that to control the playback and volume of a violin solo.

The team used the Project Soli openFrameworks example provided with the ofxSoli addon and searched for the signal that seemed to correlate closest with the tiny violin gesture. In this case it was the fine displacement signal, which then they fed the delta of to Wekinator via OSC. Theo (Design I/O) then had to train Wekinator on what types of finger movements corresponded to playing the violin and which ones it should reject. So he recorded a few different finger movements and assigned the value of 1.0 on the slider. The slider to 0.0 and recorded gestures were then set which didn’t correspond: like pulling your hand away from the sensor, or just holding it there without moving your fingers. After a few minutes of recording these gestures, the ‘training’ was initiated and they were then able to send back an animated value ranging from 0.0 to 1.0 representing how much Theo’s hand looked like it was trying to play a tiny violin. The last step was to map that number to the volume of the violin sample that was being played back by the openFrameworks app.

https://hackaday.com/2016/06/15/worlds-tiniest-violin-using-radar-and-machine-learning/

 

Computed Curation

Curating photography with neural networks

Created by Philipp Schmitt (with Margot Fabre), ‘Computed Curation’ is a photobook created by a computer. Taking the human editor out of the loop, it uses machine learning and computer vision tools to curate a series of photos from an archive of pictures.

https://philippschmitt.com/projects/computed-curation