Machine learning


2015 -




Audun Mathias Øygard

Following on the Repcol project, Principal Components looks at applying a diverse set of machine learning technologies to museum collections. It looks at how machine learning can give easier access to collections through better metadata and explorative interfaces. Concurrently it also explores the strange and uncanny artifacts and errors that arise from machine learning processes and errors.

The project would not have happened were it not for the adventurous archivists at the National Museum and the interests of our collaborating machine learning specialist Audun Mathias Øygard (@matsiyatzy).

Amongst other things the project is looking at facial similarity, automatic tagging of works based on subject as well as using classification to cluster works into neighborhoods based on style. Some of these are experimental, but others will find their way into user interfaces we are building for the National Museum's website.

Pricipal Components is still ongoing and results and further documentation will be posted here. Follow us on Twitter for updates.

Generating landscape 'paintings'

You can train neural networks to generate images. This is done by combining two networks – one learns to recognize images, while the other learns to make images that can fool it. The networks are adversaries and the technique is called Deep Convolutional Generative Adversarial Networks (DCGAN).

Given that national romantic landscapes figure prominently in the collection of the National Museum it was tempting to train a network generate new samples.