4 papers
Persistent Entropy Transform: An entropy-based descriptor for topological data analysis
Victor Toscano-Duran, Miguel A. Gutiérrez Naranjo, Rocio Gonzalez-Diaz
Persistent entropy provides a compact summary of persistence diagrams, but discards geometric information inherent to the data. This limitation creates a gap between scalar summari…
Barycentric Neural Networks and Length-Weighted Persistent Entropy Loss: A Green Geometric and Topological Framework for Function Approximation
Victor Toscano-Duran, Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo
While artificial neural networks are known as universal approximators for continuous functions, many modern approaches rely on overparameterized architectures with high computation…
Safe and Efficient Social Navigation through Explainable Safety Regions Based on Topological Features
Victor Toscano-Duran, Sara Narteni, Alberto Carlevaro +2
The recent adoption of artificial intelligence in robotics has driven the development of algorithms that enable autonomous systems to adapt to complex social environments. In parti…
Molecular Machine Learning Using Euler Characteristic Transforms
Victor Toscano-Duran, Florian Rottach, Bastian Rieck
The shape of a molecule determines its physicochemical and biological properties. However, it is often underrepresented in standard molecular representation learning approaches. He…