factual

Perceptron Limited to Linear Functions

Minsky and Papert proved that single-layer Perceptrons (with one layer of adjustable weights) are fundamentally limited to computing linear, local functions of their input and so cannot solve interesting problems; this dampened interest until Rumelhart, Hinton, and McClelland developed learning algorithms for multilayer networks that could solve those more complex problems, leading 40 years later to modern AI mainly through scale.

factualpending

Speaker

Tom Griffiths

Evidence Quote

“another bunch of psychologists, David Rumelhart, working with Geoff Hinton... they started exploring these models and then came up with learning algorithms for multilayer neural networks that could then solve these more complex problems.”

Source

343 | Tom Griffiths on The Laws of Thought— Sean Carroll's Mindscape
Created: 6/13/2026, 12:12:58 AM

Your notes

Loading notes...