Stanford CS230 | Autumn 2025 | Lecture 10: What’s Going On Inside My Model?

Stanford Online · 106:53

CNN interpretability is mature and visual (saliency, occlusion, CAM, gradient-ascent “what is a dog?”, dataset search, deconv), but those tools do not transfer cleanly to today’s 100B+ models—so a frontier trainer deb...

Read the full summary on tuber

Redirecting...