no code implementations • 27 Jan 2023 • Adrián Inés, César Domínguez, Jónathan Heras, Gadea Mata, Julio Rubio
In this paper we describe the mathematical foundations of a new approach to semi-supervised Machine Learning.
no code implementations • 19 May 2022 • Adrián Inés, Andrés Díaz-Pinto, César Domínguez, Jónathan Heras, Eloy Mata, Vico Pascual
By combining semi-supervised learning methods with compact networks, it is possible to obtain a similar performance to standard size networks.
1 code implementation • 19 May 2022 • Adrián Inés, César Domínguez, Jónathan Heras, Gadea Mata, Julio Rubio
In the former, we have used a homological approach that consists in studying the persistence diagrams associated with the data using the Bottleneck and Wasserstein distances.