Rational Animations
patreon
What Do Neural Networks Really Learn? Exploring the Brain of an AI Model
🕑 Added 2024-06-14 15:43:14 +0000 UTCIn our new video, we talk about research on interpreting InceptionV1, a convolutional neural network. Researchers have been able to understand the function of neurons and channels inside the network and uncover visual processing algorithms by looking at the weights. The work on InceptionV1 is early but landmark mechanistic interpretability research, and it functions well as an introduction to the field. We also go into the rationale and goals of the field and mention some more recent research near the end.
Comments
Long Hoang
this was a great one! love more of those digestible deep dives into papers!
