We are interested in finding different mathematical approaches to learning inspired by modern Mathematics, Neuroscience
We are building new frameworks for learning from data and formal knowledge. Our strategy is to look for the mathematical properties that directly allow generalization, as in algebraic.ai using techniques from Universal Algebra/Model Theory.
We are a group of Physicists, Mathematicians, and Biologists at Champalimaud Foundation in Lisbon.
Some of our applications are in the field of quantitative measurement of behavior as in idtracker.ai, and in collective intelligence. This complements our previous work in this field like this, this, even this, or this other one. Before this work, we enjoyed thinking about neuronal coding, deviations from optimality in biology, wiring economy and quantum mechanics.
You can also find more of our work present and past at google scholar.
If you are interested, please contact us at firstname.lastname@example.org
Champalimaud Centre for the Unknown
Avenida Brasília, 1400-038 Lisbon, Portugal
T (+351) 210 480 200