Text Topography

Next step: create a corpus, and feed into a CycleGAN with landscape paintings &amp; photographs as the other, so you can turn a book into a landscape.<p>Final step: since CycleGAN goes both directions, you can decode an arbitrary landscape painting into a &#x27;book&#x27; and use a language model to fill in all the words with the highest-probability word that fits.

It&#x27;d be interesting to see if persistent homology can be found in this representation (like it often can be found in phase-delay representations of time-series).

This article uses &quot;aesthetic&quot; as an adjective... am I the only one who finds this irritating?