factual

Neural Networks Are Hard to Interpret

Modern real-world neural networks contain millions or even billions of weights, making it very difficult to figure out what they are actually doing or why they succeed, unlike symbolic AI where humans explicitly build in interpretable rules.

factualpending

Speaker

Melanie Mitchell

Evidence Quote

“that is somehow included in these billions of weights, in a way that's very hard to visualize or pinpoint.”

Source

68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense— Sean Carroll's Mindscape
Created: 6/13/2026, 12:06:58 AM

Your notes

Loading notes...