✳flâneur — a map of the web's best reading

Google Brain Residency | Ryan Dahl

tinyclouds.org · 2,900 words · saved by 1 readers

Last year, after nerding out a bit on TensorFlow, I applied and was accepted into the inaugural class of the Google Brain Residency Program. The program invites two dozen people, with varying backgrounds in ML, to spend a year at Google's deep learning research lab in Mountain View to work with the scientists and engineers pushing on the forefront of this technology. The year has just concluded and this is a summary of how I spent it. The motivating goal/demo I have in mind is to clean up old movies and TV shows. Imagine seeing grainy TV shows from the 90s, or black and white movies from the 1960s, in lush and colorful 4K resolution. This seems entirely plausible: we can take good modern media and distort it to be grainy, low-resolution, or black and white, and train a supervised model to do the reverse transformation. Training data is practically infinite. This would be awesome. Don't get too excited--the technology isn't there yet... but it's getting closer. Armed with little more th

Google Brain Residency | Ryan Dahl ← Back 🌓 Google Brain Residency 2017-06-06 Last year, after nerding out a bit on TensorFlow, I applied and was accepted into the inaugural class of the Google Brain Residency Program . The program invites two dozen people, with varying backgrounds in ML, to spend a year at Google's deep learning research lab in Mountain View to work with the scientists and engineers pushing on the forefront of this technology. The year has just concluded and this is a summary of how I spent it. The motivating goal/demo I have in mind is to clean up old movies and TV shows. I

Explore this link on the map →

related reading