DCGAN for Archaeologists

2018-07-29 Learning about GANs Melvin Wevers has been using neural networks to understand visual patterns in the evolution of newspaper advertisements in Holland. He and his team developed a tool for visually searching the newspaper corpus. Melvin presented some of his research at #dh2018; he shared his poster and slides so I was able to have a look. Afterwards, I reached out to Melvin and we had a long conversation about using computer vision in historical research. »

Tensorflow for Poets

2018-06-14 In our recent paper, ‘Fleshing Out the Bones’ we used the trained ‘Inception 3’ model as a way of determining clusters of images that we then studied for clues and hints: why did the machine cluster them this way? What are the common features? Unsupervised learning: It’s not unlike reading entrails. An alternate approach is to take an existing model, and add new training data to it. Pete Warden put together a tutorial a few years ago called Tensorflow for Poets that has since been formalized as a Google CodeLabs tutorial. »

Using Etudier to Jump Start a Literature Review

2018-04-30 The Literature Review How do you start a literature review on a new project? We’re not starting from scratch, of course - we’ve got the pages of bibliography that we generated when we first starting scratching out what this project could be about. We started that step by considering the bibliography we had to hand as we wrote our first paper. Nothing is ever truly from scratch, in academia. »

Getting Started!

2018-04-16 We’re underway! We received word at the end of March that this project has been funded. Since then, we’ve been doing the administrative work to get the project up and running - figuring out how to advertise for students, how to enable those students to study at Stockholm for a term or two, setting up the public face of this project, figuring out the internals of the research accounting system. »