FAI: Foundational AI

Our goal is to develop artificial intelligence capable of learning to accomplish complex tasks, with the amount of supervision being comparable to (or less than) what typical humans require to solve such tasks.

Research topics:

  • Unsupervised learning as evolution of complex systems,
  • Diversity in evolutionary learning algorithms,
  • Measures of complexity growth in various computational systems. Applications include simulated environments where agents accomplish goals (for example, the Atari games benchmark).

 

Head of the group

Name: Tomas Mikolov
Email: tomas.mikolov(at)cvut.cz

PI: Tomas Mikolov 

Staff: Hugo Cisneros, Barbora Hudcová