Inductive logic programming approaches to learning from symbol strings were less computationally efficient than neural approaches even in the small-scale problems of the 1980s-1990s, but symbolic approaches could not scale to modern problems like ImageNet classification.
factualpending
Speaker
Geoffrey HintonEvidence Quote
“for a problem of the scale I was using they probably were but as things scaled up it became very clear that that approach...is a much better way to model language than having rules for manipulating simple strings”
Source
Geoff Hinton - Will Digital Intelligence Replace Biological Intelligence? | Vector's Remarkable 2024— Vector InstituteCreated: 8/11/2026, 7:34:33 AM
Your notes
Loading notes...