How a simple game of 20 questions could help make AI fit for the future

EngineeringNews newsroom brief · 2h ago · 1 min read · via phys.org

Artificial intelligence programs used to classify images could be trained much more cheaply using a surprisingly simple method inspired by the childhood game of 20 Questions, according to new research posted to the arXiv preprint server by a team from the University of Bristol.

Artificial intelligence programs used to classify images could be trained much more cheaply using a surprisingly simple method inspired by the childhood game of 20 Questions, according to new research posted to the arXiv preprint server by a team from the University of Bristol. This story matters for Science & Discovery readers tracking engineering. Reported by phys.org. Read the full original at the source link below.

Originally reported by phys.org. EngineeringNews curates and briefs the science & discovery stories that matter. Our editorial policy →
Get the daily engineering signal:

More from EngineeringNews

Across the eCorp newsroom network

Part of the eCorp network