activity
20212026
collaborators

7 papers

cs.LG2026

Concept Inconsistency in Dermoscopic Concept Bottleneck Models: A Rough-Set Analysis of the Derm7pt Dataset

Gonzalo Nápoles, Isel Grau, Yamisleydi Salgueiro

Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label consistency. When a dataset co…

cs.LG2022

Which is the best model for my data?

Gonzalo Nápoles, Isel Grau, Çiçek Güven +2

In this paper, we tackle the problem of selecting the optimal model for a given structured pattern classification dataset. In this context, a model can be understood as a classifie…

stat.AP2021

Measuring Wind Turbine Health Using Drifting Concepts

Agnieszka Jastrzebska, Alejandro Morales-Hernández, Gonzalo Nápoles +2

Time series processing is an essential aspect of wind turbine health monitoring. Despite the progress in this field, there is still room for new methods to improve modeling quality…

cs.LG2021

Forward Composition Propagation for Explainable Neural Reasoning

Isel Grau, Gonzalo Nápoles, Marilyn Bello +2

This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification prob…

cs.LG2021

Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classification

Gonzalo Nápoles, Yamisleydi Salgueiro, Isel Grau +1

Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most ac…

cs.LG2021

Online learning of windmill time series using Long Short-term Cognitive Networks

Alejandro Morales-Hernández, Gonzalo Nápoles, Agnieszka Jastrzebska +2

Forecasting windmill time series is often the basis of other processes such as anomaly detection, health monitoring, or maintenance scheduling. The amount of data generated on wind…

cs.LG2021

Long Short-term Cognitive Networks

Gonzalo Nápoles, Isel Grau, Agnieszka Jastrzebska +1

In this paper, we present a recurrent neural system named Long Short-term Cognitive Networks (LSTCNs) as a generalization of the Short-term Cognitive Network (STCN) model. Such a g…