NOVA Math hosted a captivating Seminar of Algebra and Logic featuring Fernando Martin-Maroto from the Champalimaud Foundation and Algebraic AI.
A Glimpse into Algebraic Machine Learning (AML)
Fernando provided a fascinating introduction to AML, a unique approach to machine learning that eschews traditional statistical methods in favor of pure algebra.
Key Highlights of AML:
- Purely Algebraic: AML is rooted in algebraic principles, offering a fresh perspective on machine learning.
- Versatile Learning: AML can learn from both data and problem statements, making it adaptable to a wide range of applications.
- Impressive Performance: AML has demonstrated remarkable results over the last few years.
Atomized Semilatices: The Mathematical Foundation
Fernando also delved into Atomized Semilatices, the mathematical framework that underpins AML. This powerful tool enables efficient operations and computations within AML models.
Want to Learn More?
If you're intrigued by the potential of Algebraic Machine Learning, we encourage you to explore further. Stay tuned for future events and publications from NOVA Math and the ALMA Consortium.
The ALMA project is a project of the European Commission based on a new AI method called Algebraic Machine Learning (AML). AML is not based on neural networks and is not a statistical learning method; it is a purely algebraic method that allows learning from data and formal descriptions. With the ALMA project, the European Commission wants to leverage the unique properties of AML to build an AI of the future that is more transparent and more capable of working together with humans.
MORE INFORMATION:
To know more about the Champalimaud Foundation click here.
To know more about NOVA School of Science and Technology click here.
For any questions about ALMA please contact
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 952091.