factual

Neural net power comes from differentiability, not inscrutability

It is a common misconception that the power of neural networks comes from their inscrutability; in fact their power comes from their differentiability—being a black box with many knobs that can be continuously tuned until they perform well—so it should be possible to combine deep learning's ability to discover solutions with a subsequent step that simplifies those solutions into human-understandable, intelligible forms, exactly as a human can both learn to catch a ball and then explain its parabolic path with an equation.

factualpending

Speaker

Max Tegmark

Evidence Quote

“the power of them doesn't come from their inscrutability, but from their differentiability”

Source

75 | Max Tegmark on Reality, Simulation, and the Multiverse— Sean Carroll's Mindscape
Created: 6/13/2026, 12:10:24 AM

Your notes

Loading notes...