A topological model for partial equivariance in deep learning and data analysis
Ferrari, Lucia, Frosini, Patrizio, Quercioli, Nicola, Tombari, Francesca
–arXiv.org Artificial Intelligence
In this article, we propose a topological model to encode partial equivariance in neural networks. To this end, we introduce a class of operators, called P-GENEOs, that change data expressed by measurements, respecting the action of certain sets of transformations, in a non-expansive way. If the set of transformations acting is a group, then we obtain the so-called GENEOs. We then study the spaces of measurements, whose domains are subject to the action of certain self-maps, and the space of P-GENEOs between these spaces. We define pseudo-metrics on them and show some properties of the resulting spaces. In particular, we show how such spaces have convenient approximation and convexity properties.
arXiv.org Artificial Intelligence
Aug-25-2023
- Country:
- Asia > Singapore (0.04)
- North America > United States
- New York > New York County > New York City (0.04)
- Europe
- Germany > Hamburg (0.04)
- Italy > Emilia-Romagna
- Metropolitan City of Bologna > Bologna (0.04)
- Genre:
- Research Report (0.40)
- Technology: