Blade Runner - Autoencoded at the Whitney Museum (Patreon)

I saw a screening of Blade Runner - Autoencoded at the Whitney Museum in New York. I had no idea what to expect—the only information about it was this:

The artist and computer scientist Terence Broad built an autoencoder, a type of artificial neural network, and showed it the classic science-fiction film Blade Runner (1982). He trained the autoencoder to remember every individual frame of the film and to reconstruct each one as a memory, on view here. In the original film, a bounty hunter hunts down androids that are so well engineered that they are indistinguishable from humans. Here, we face a similar challenge, as we trying to identify the original film within the AI’s program’s perception of it.

In the video above, the regular version is on the left and the autoencoded version is on the right. The whole movie looked like just the right side. As far as I could tell, much of the audience was as clueless as I was. Within the first half hour, most of the theater emptied. I actually found it really interesting. Seeing as I had recently made a video on Blade Runner, the film was still fresh in my mind and because making the video required me to re-watch scenes over and over, collect screenshots, and scrutinize all of the details of the film, I was able to visualize everything that I should have been seeing. It was like the film was guiding me through my own memory of it, which is something I’ve never experienced before. 

Here is an interesting article by the person who made it with more examples: bit.ly/2i6Masx

The Whitney Museum also had a selection of original concept art by Syd Mead, which was really amazing to see in person. I tried to take some pictures. They were behind glass, so there was reflection. 

Here they are:

Thanks so much for your continued support!