Actions

The Algoliterator

From Algolit

Revision as of 18:46, 13 March 2019 by An (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

by Algolit

The Algoliterator is a neural network trained using the selection of digitized works of the Mundaneum archive.

With the Algoliterator you can write a text in the style of the International Institutions Bureau. The Algoliterator starts by selecting a sentence from the archive or corpus used to train it. You can then continue writing yourself or, at any time, ask the Algoliterator to suggest a next sentence: the network will generate three new fragments based on the texts it has read. You can control the level of training of the network and have it generate sentences based on primitive training, intermediate training or final training.

When you're satisfied with your new text, you can print it on the thermal printer and take it home as a souvenir.


Sources: https://gitlab.constantvzw.org/algolit/algoliterator.clone

Concept, code & interface: Gijs de Heij & An Mertens

Technique: Recurrent Neural Network

Original model: Andrej Karphaty, Justin Johnson