Text reproduction with machine learning

From Hackers & Designers
Revision as of 21:02, 17 July 2018 by Juliette (talk | contribs) (Created page with "{{Event |Name=Text reproduction with machine learning |Location=De Bonte Zwaan |Date=2018/07/31 |Time=10:00-17:00 |PeopleOrganisations=Moritz Ebeling |Type=HDSA2018 |Web=Yes |...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Text reproduction with machine learning
Name Text reproduction with machine learning
Location De Bonte Zwaan
Date 2018/07/31
Time 10:00-17:00
PeopleOrganisations Moritz Ebeling
Type HDSA2018
Web Yes
Print No

In the era of data, intelligence and computing, the authenticity of any digital content is not longer guaranteed. With machine learning technology, a human voice can be imitated, an moving image can be manipulated in real time, texts can be phrased by using raw data. All to make up something „real“. To get a glimpse of what’s going on, let’s build our own deep learning network! In this workshop, we will train a given neural network on original text to reproduce it, remix it, produce more of it. Sometimes the output will be complete rubbish, sometimes the algorithm will repeat passgages from the original. But certainly it will invent or rehash content based on the given input, so who is faking whom? This workshop can be fun for beginners and pros.

Please bring – A computer + power plug – Know where to find your computer’s Terminal or Console – Have Python 3 installed (1) – We will use Tensorflow, so if you’re cool with Python, you can install it already, otherwise we do it during the workshop or in advance. – Text material that you want to feed the machine with. This can be text that you wrote yourself or found somewhere. Short text passages will be internalized by the machine very quickly, so this can be a good experiment but might not be that interesting to fill a whole day. So bring more text, a few pages or a book, or even more. Think of text that you want to remix, reproduce and produce more of. E.g. all surrealist poems from Pablo Neruda, The Communist Mannifesto by Karl Marx, the scripts from all Harry Potter movies, Newspaper headlines from the last year, whatever. We will need the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text whatever you like, as long as its in one or many .txt files.

(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.

Moritz.jpg