"The YouTube system is built on top of Google Brain, or as we now know it, TensorFlow. To give an idea of scale, the models learn approximately one billion parameters and are trained on hundreds of billions of examples. The basic problem is posed as 'given this user's YouTube activity history, which videos are they most likely to watch next?'" The recommendations are (in my experience) not so great - they reflect my YouTube interests, but not my wider interests. The full paper is available from Google (8 page PDF)
Today: 6 Total: 120 [Direct link] [Share]
View full size
