4 papers
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
David Méndez, Roberto Confalonieri, Natalia DÃaz RodrÃguez
Vision-Language Models (VLMs) excel at tasks like zero-shot classification and cross-modal retrieval by mapping images and text to a shared space, but this requires expensive end-t…
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
David Mendez, Fernando Martin-Maroto, Gonzalo G. de Polavieja
Symbolic methods are generally not considered competitive with strong modern learners on realistic supervised tasks. We evaluate Algebraic Machine Learning (AML), a framework that…
Infinite Atomized Semilattices
Fernando Martin-Maroto, Antonio Ricciardo, David Mendez +1
We extend the theory of atomized semilattices to the infinite setting. We show that it is well-defined and that every semilattice is atomizable. We also study atom redundancy, focu…
Algebraic Machine Learning: Learning as computing an algebraic decomposition of a task
Fernando Martin-Maroto, Nabil Abderrahaman, David Mendez +1
Statistics and Optimization are foundational to modern Machine Learning. Here, we propose an alternative foundation based on Abstract Algebra, with mathematics that facilitates the…