Author name cluster

Pablo M. Olmos

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

JBHI Journal 2025 Journal Article

Alzheimer's Disease Detection in EEG Sleep Signals

Lorena Gallego-Viñarás
Juan Miguel Mira-Tomás
Anna Michela Gaeta
Gerard Pinol-Ripoll
Ferran Barbé
Pablo M. Olmos
Arrate Muñoz-Barrutia

Alzheimer's disease (AD) and sleep disorders exhibit a close association, where disruptions in sleep patterns often precede the onset of Mild Cognitive Impairment (MCI) and early-stage AD. This study delves into the potential of utilizing sleep-related electroencephalography (EEG) signals acquired through polysomnography (PSG) for the early detection of AD. Our primary focus is on exploring semi-supervised Deep Learning techniques for the classification of EEG signals due to the clinical scenario characterized by the limited data availability. The methodology entails testing and comparing the performance of semi-supervised models, benchmarked against an unsupervised and a supervised model. The study highlights the significance of spatial and temporal analysis capabilities, conducting independent analyses of each sleep stage. Results demonstrate the effectiveness of one semi-supervised model in leveraging limited labeled data, achieving stable metrics across all sleep stages, and reaching 90% accuracy in its supervised form. Comparative analyses reveal this superior performance over the unsupervised model, while the supervised model ranges between $92-94\%$. These findings underscore the potential of semi-supervised models in early AD detection, particularly in overcoming the challenges associated with the scarcity of labeled data. Ablation tests affirm the critical role of spatio-temporal feature extraction in semi-supervised predictive performance, and t-SNE visualizations validate the model's proficiency in distinguishing AD patterns. Overall, this research contributes to the advancement of AD detection through innovative Deep Learning approaches, highlighting the crucial role of semi-supervised learning in addressing data limitations.

Details DOI

UAI Conference 2025 Conference Paper

Improved Variational Inference in Discrete VAEs using Error Correcting Codes

María Martínez-García
Grace Villacrés
David G. M. Mitchell
Pablo M. Olmos

Despite advances in deep probabilistic models, learning discrete latent representations remains challenging. This work introduces a novel method to improve inference in discrete Variational Autoencoders by reframing the inference problem through a generative perspective. We conceptualize the model as a communication system, and propose to leverage Error-Correcting Codes (ECCs) to introduce redundancy in latent representations, allowing the variational posterior to produce more accurate estimates and reduce the variational gap. We present a proof-of-concept using a Discrete Variational Autoencoder with binary latent variables and low-complexity repetition codes, extending it to a hierarchical structure for disentangling global and local data features. Our approach significantly improves generation quality, data reconstruction, and uncertainty calibration, outperforming the uncoded models even when trained with tighter bounds such as the Importance Weighted Autoencoder objective. We also outline the properties that ECCs should possess to be effectively utilized for improved discrete variational inference.

Details

ICML Conference 2024 Conference Paper

Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks

Mikkel Jordahn
Pablo M. Olmos

Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model accuracy is of extreme importance and interest in safety critical applications such as in the health-care sector. In this work, we show that decoupling the training of feature extraction layers and classification layers in over-parametrized DNN architectures such as Wide Residual Networks (WRN) and Vision Transformers (ViT) significantly improves model calibration whilst retaining accuracy, and at a low training cost. In addition, we show that placing a Gaussian prior on the last hidden layer outputs of a DNN, and training the model variationally in the classification training stage, even further improves calibration. We illustrate these methods improve calibration across ViT and WRN architectures for several image classification benchmark datasets.

Details

ICLR Conference 2024 Conference Paper

Efficient local linearity regularization to overcome catastrophic overfitting

Elías Abad-Rocamora
Fanghui Liu 0001
Grigorios Chrysos 0002
Pablo M. Olmos
Volkan Cevher

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to $0$%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly with respect to the input, this is however lost in single-step AT. To address CO in single-step AT, several methods have been proposed to enforce local linearity of the loss via regularization. However, these regularization terms considerably slow down training due to *Double Backpropagation*. Instead, in this work, we introduce a regularization term, called ELLE, to mitigate CO *effectively* and *efficiently* in classical AT evaluations, as well as some more difficult regimes, e.g., large adversarial perturbations and long training schedules. Our regularization term can be theoretically linked to curvature of the loss function and is computationally cheaper than previous methods by avoiding *Double Backpropagation*. Our thorough experimental validation demonstrates that our work does not suffer from CO, even in challenging settings where previous works suffer from it. We also notice that adapting our regularization parameter during training (ELLE-A) greatly improves the performance, specially in large $\epsilon$ setups. Our implementation is available in https://github.com/LIONS-EPFL/ELLE.

Details

EAAI Journal 2023 Journal Article

Automatic antibiotic resistance prediction in Klebsiella pneumoniae based on MALDI-TOF mass spectra

Alejandro Guerrero-López
Carlos Sevilla-Salcedo
Ana Candela
Marta Hernández-García
Emilia Cercenado
Pablo M. Olmos
Rafael Cantón
Patricia Muñoz

Matrix-Assisted Laser Desorption Ionization Time-Of-Flight (MALDI-TOF) Mass Spectrometry (MS) is a reference method for microbial identification and it can be used to predict Antibiotic Resistance (AR) when combined with artificial intelligence methods. However, current solutions need time-costly preprocessing steps, are difficult to reproduce due to hyperparameter tuning, are hardly interpretable, and do not pay attention to epidemiological differences inherent to data coming from different centres, which can be critical. We propose using a multi-view heterogeneous Bayesian model (KSSHIBA) for the prediction of AR using MALDI-TOF MS data together with their epidemiological differences. KSSHIBA is the first model that removes the ad-hoc preprocessing steps that work with raw MALDI-TOF data. In addition, due to its Bayesian probabilistic nature, it does not require hyperparameter tuning, provides interpretable results, and allows exploiting local epidemiological differences between data sources. To test the proposal, we used data from 402 Klebsiella pneumoniae isolates coming from two different domains and 20 different hospitals located in Spain and Portugal. KSSHIBA outperforms current state-of-the-art approaches in antibiotic susceptibility prediction, obtaining a 0. 78 AUC score in Wild Type classification and a 0. 90 AUC score in Extended-Spectrum Beta-Lactamases (ESBL)+Carbapenemases (CP)-producers. The proposal consistently removes the need for ad-hoc preprocessing by working with raw MALDI-TOF data, which, in turn, reduces the time needed to obtain the results of the resistance mechanism in microbiological laboratories. The proposed model implementation as well as both data domains are publicly available.

Details DOI

EAAI Journal 2023 Journal Article

Detecting train driveshaft damages using accelerometer signals and Differential Convolutional Neural Networks

Antía López Galdo
Alejandro Guerrero-López
Pablo M. Olmos
María Jesús Gómez García

Maintaining railway axles is crucial to prevent catastrophic failures and enormous human and economic costs. In recent years, there has been a growing interest in the railway industry to adopt condition monitoring techniques to enhance the safety and efficiency of the rail transport system, which maintenance is currently based on periodic inspections. In this context, this work presents a technique for real-time crack diagnosis on railway axles, based on advanced 2D-Convolutional Neural Network (CNN) architectures applied to time–frequency representations of vibration signals. One of the critical novelties is introducing a differential CNN structure that captures the system’s statistical properties, enabling generalisation between different mechanical sets and conditions. The proposed system has been trained with data corresponding to a unique wheelset assembly, showing that the model is able to diagnose cracks on the three different wheelset tested in operation under 32 different combinations of conditions, such as load, speed, sense of rotation and vibration direction. Four different crack levels have been introduced, representing the maximum one a 0. 08% of the axle diameter, and the method proposed achieved Area Under the Curve (AUC) score of 0. 85, significantly outperforming results obtained with other architectures proposed in the state-of-the-art, the score of the next below is 0. 76. The results demonstrate the effectiveness and practicality of this approach to accurately classify the four crack levels tested within a condition monitoring system for non-stationary conditions, that would enable reliable real-time diagnosis, thus paving the way towards a more robust and efficient railway axle maintenance system.

Details DOI

JBHI Journal 2023 Journal Article

Handling Ill-Conditioned Omics Data With Deep Probabilistic Models

María Martínez-García
Pablo M. Olmos

The advent of high-throughput technologies has produced an increase in the dimensionality of omics datasets, which limits the application of machine learning methods due to the great unbalance between the number of observations and features. In this scenario, dimensionality reduction is essential to extract the relevant information within these datasets and project it in a low-dimensional space, and probabilistic latent space models are becoming popular given their capability to capture the underlying structure of the data as well as the uncertainty in the information. This article aims to provide a general classification and dimensionality reduction method based on deep latent space models that tackles two of the main problems that arise in omics datasets: the presence of missing data and the limited number of observations against the number of features. We propose a semi-supervised Bayesian latent space model that infers a low-dimensional embedding driven by the target label: the Deep Bayesian Logistic Regression (DBLR) model. During inference, the model also learns a global vector of weights that allows it to make predictions given the low-dimensional embedding of the observations. Since this kind of dataset is prone to overfitting, we introduce an additional probabilistic regularization method based on the semi-supervised nature of the model. We compared the performance of the DBLR against several state-of-the-art methods for dimensionality reduction, both in synthetic and real datasets with different data types. The proposed model provides more informative low-dimensional representations, outperforms the baseline methods in classification, and can naturally handle missing entries.

Details DOI

ICML Conference 2023 Conference Paper

Variational Mixture of HyperGenerators for Learning Distributions over Functions

Batuhan Koyuncu
Pablo Sánchez-Martín
Ignacio Peis
Pablo M. Olmos
Isabel Valera

Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally costly when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VaMoH. VaMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VaMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VaMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VaMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.

Details

JBHI Journal 2022 Journal Article

Medical Data Wrangling With Sequential Variational Autoencoders

Daniel Barrejon
Pablo M. Olmos
Antonio Artes-Rodriguez

Medical data sets are usually corrupted by noise and missing data. These missing patterns are commonly assumed to be completely random, but in medical scenarios, the reality is that these patterns occur in bursts due to sensors that are off for some time or data collected in a misaligned uneven fashion, among other causes. This paper proposes to model medical data records with heterogeneous data types and bursty missing data using sequential variational autoencoders (VAEs). In particular, we propose a new methodology, the Shi-VAE, which extends the capabilities of VAEs to sequential streams of data with missing observations. We compare our model against state-of-the-art solutions in an intensive care unit database (ICU) and a dataset of passive human monitoring. Furthermore, we find that standard error metrics such as RMSE are not conclusive enough to assess temporal models and include in our analysis the cross-correlation between the ground truth and the imputed signal. We show that Shi-VAE achieves the best performance in terms of using both metrics, with lower computational complexity than the GP-VAE model, which is the state-of-the-art method for medical records.

Details DOI

JBHI Journal 2019 Journal Article

Deep Sequential Models for Suicidal Ideation From Multiple Source Data

Ignacio Peis
Pablo M. Olmos
Constanza Vera-Varela
Maria Luisa Barrigon
Philippe Courtet
Enrique Baca-Garcia
Antonio Artes-Rodriguez

This paper presents a novel method for predicting suicidal ideation from electronic health records (EHR) and ecological momentary assessment (EMA) data using deep sequential models. Both EHR longitudinal data and EMA question forms are defined by asynchronous, variable length, randomly sampled data sequences. In our method, we model each of them with a recurrent neural network, and both sequences are aligned by concatenating the hidden state of each of them using temporal marks. Furthermore, we incorporate attention schemes to improve performance in long sequences and time-independent pre-trained schemes to cope with very short sequences. Using a database of 1023 patients, our experimental results show that the addition of EMA records boosts the system recall to predict the suicidal ideation diagnosis from 48. 13% obtained exclusively from EHR-based state-of-the-art methods to 67. 78%. Additionally, our method provides interpretability through the t-distributed stochastic neighbor embedding (t-SNE) representation of the latent space. Furthermore, the most relevant input features are identified and interpreted medically.

Details DOI