Early vision in artificial neural networks
Seminar | January 22 | 12-1 p.m. | 560 Evans Hall
Chris Olah, Open AI
Artificial neural networks are capable of sophisticated vision tasks, including recognizing complex object families and captioning images. But very little is known about how they accomplish this. What happens if we take such a neural network seriously as a kind of "model organism?" In this talk, we give a neuron by neuron account of low-level visual features in InceptionV1, and demonstrate that the algorithms implementing these features can be read off from the circuits of weights connecting them.