Posted on by Rafael Scapin

A neural network learns when it should not be trusted

A faster way to estimate uncertainty in AI-assisted decision-making could lead to safer outcomes.

https://news.mit.edu/2020/neural-network-uncertainty-1120

Related Posts:

  1. From Bricks to Clicks – The Potential of Data and Analytics in Higher Education
  2. A network of artificial neurons learns to use human language
  3. Towards a Trusted Framework for Identity and Data Sharing
  4. Presentation of the Week: Trusted Learning Analytics
  5. A neural portrait of the human mind