← Search

Peter Norvig

2 accepted papers

2026

Position: There are futures that benchmark-driven AI cannot see

ICML 2026oral

Breakthroughs often come from ideas we could not have predicted in advance. In biology, this is called exaptation: traits evolved for one function become decisive for another. Scientific progress works similarly, but only if ideas survive periods when they appear uncompetitive by current metrics. Th…

Cited by 0Source ↗Scholar ↗
2017

Deep Learning with Dynamic Computation Graphs

ICLR 2017poster

Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not direct…

Cited by 172Source ↗code ↗Scholar ↗