DeepMind Blog company blog

Measuring abstract reasoning in neural networks

Neural network-based models continue to achieve impressive results on longstanding machine learning problems, but establishing their capacity to reason about abstract concepts has proven difficult. Building on previous efforts to solve this important feature of general-purpose learning systems, our latest paper sets…
Points
127
HN comments
25
Submissions
1
Cited by
0 commenters

AI & Machine LearningScience & Space2018

On Hacker News

SubmittedTitle on HNPointsComments
Jul 14, 2018Measuring abstract reasoning in neural networks by ZeljkoS12725

More from DeepMind Blog

All 56 posts →

Related posts from the same era