Actions

The Algoliterator: Difference between revisions

From Algolit

(Created page with "The Algoliterator by Gijs de Heij & An Mertens, Algolit The Algoliterator is trained using a neural network and the selection of digitized works of the Mundaneum archive....")
 
(Slight rewrite, removed the line on printing.)
Line 2: Line 2:
 
by Gijs de Heij & An Mertens, Algolit
 
by Gijs de Heij & An Mertens, Algolit
  
The Algoliterator is trained using a neural network and the selection of digitized works of the Mundaneum archive.  
+
The Algoliterator is an interface to a neural network trained using the selection of digitized works of the Mundaneum archive.  
  
The ALgoliterator helps you to write a text in the style of the International Institutions Bureau. You can choose a start sentence from that oeuvre, you can also choose whether you want the Algoliterator to produce the following sentences based on primitive training, intermediate training or final training. The machine proposes a paragraph that you can edit. If you are happy with the result, you can send it to the thermal printer and take the text home as a souvenir.
+
With the Algoliterator you can write a text in the style of the International Institutions Bureau. The Algoliterator starts by picking a sentence from the archive or corpus it was trained on. 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 level of training of the network and have it generate sentences based on primitive training, intermediate training or final training.
  
 
Sources: https://gitlab.constantvzw.org/algolit/algoliterator.clone
 
Sources: https://gitlab.constantvzw.org/algolit/algoliterator.clone

Revision as of 15:18, 1 March 2019

The Algoliterator by Gijs de Heij & An Mertens, Algolit

The Algoliterator is an interface to 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 picking a sentence from the archive or corpus it was trained on. 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 level of training of the network and have it generate sentences based on primitive training, intermediate training or final training.

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