Roberto Santana

University of the Basque Country | UPV/EHU · Computer Sciences and Artificial Intelligence

This work aims to advance the optimisation of the efficiency of thermal installations in buildings, contributing to the achievement of Zero Energy Buildings (ZEB) in the context of maintenance and operation. This is achieved through an innovative proposal that merges machine learning techniques with thermoeconomics to perform diagnoses in building...

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out‐of‐distribution inputs. In this paper, we comprehensively review the possibilities and limits of...

Generalization is a key property of machine learning models to perform accurately on unseen data. Conversely, in the field of scientific machine learning (SciML), generalization entails not only predictive accuracy but also the capacity of the model to encapsulate underlying physical principles. In this paper, we delve into the concept of generaliz...

Regular vine copulas (R-vines) provide a comprehensive framework for modeling high-dimensional dependencies using a hierarchy of trees and conditional pair-copulas. While the graphical structure of R-vines is traditionally derived from data, this work introduces a novel approach by utilizing a (conditional) pairwise dependence list. Our primary goa...

In cognitive neuroscience and brain-computer interface research, accurately predicting imagined stimuli is crucial. This study investigates the effectiveness of Domain Adaptation (DA) in enhancing imagery prediction using primarily visual data from fMRI scans of 18 subjects. Initially, we train a baseline model on visual stimuli to predict imagined...

Morphometry is fundamental for studying and correlating neuronal morphology with brain functions. With increasing computational power, it is possible to extract morphometric characteristics automatically, including features such as length, volume, and number of neuron branches. However, to the best of our knowledge, there is no mapping of morphomet...

In this paper we introduce a word embedding composition method based on the intuitive idea that a fair embedding representation for a given set of words should satisfy that the new vector will be at the same distance of the vector representation of each of its constituents, and this distance should be minimized. The embedding composition method can...

This chapter introduces the use of Evolutionary Machine Learning (EML) techniques for unsupervised machine learning tasks. First, a brief introduction to the main concepts related to unsupervised Machine Learning (ML) is presented. Then, an overview of the main EML approaches to these tasks is given together with a discussion of the main achievemen...

Restricted Boltzmann Machines are generative models that consist of a layer of hidden variables connected to another layer of visible units, and they are used to model the distribution over visible variables. In order to gain a higher representability power, many hidden units are commonly used, which, in combination with a large number of visible u...

In some machine learning applications the availability of labeled instances for supervised classification is limited while unlabeled instances are abundant. Semi-supervised learning algorithms deal with these scenarios and attempt to exploit the information contained in the unlabeled examples. In this paper, we address the question of how to evolve...

Physics-Informed Neural Networks (PINNs) are Neural Network architectures trained to emulate solutions of differential equations without the necessity of solution data. They are currently ubiquitous in the scientific literature due to their flexible and promising settings. However, very little of the available research provides practical studies th...

With neural architecture search (NAS) methods gaining ground on manually designed deep neural networks—even more rapidly as model sophistication escalates—the research trend is shifting toward arranging different and often increasingly complex NAS spaces. In this conjuncture, delineating algorithms which can efficiently explore these search spaces...

p>In this paper, for the first time, a feature selection (FS) problem for an unattributed-identity multi-target regression (UIMTR) problem is presented. UIMTR is defi?ned as a multi-target regression problem where the set of target and predictor variables are undetermined, i.e., the identity of the variables is unattributed. Two forward selection ?...

p>With the advent of new loads and generation on the low voltage grid, voltage fluctuation has increased, especially in active distribution grids with a high penetration of distributed resources and a large deployment of electric vehicles. The coordination of different technologies has emerged as the best way for voltage regulation, among others, s...

This paper proposes two novel machine learning algorithms, namely Random Vector Functional Link Forests and Extreme Learning Forests, to develop an improved unmanned aerial vehicles automatic target recognition system. Such models take advantage of the stochastic procedure followed by Random Forests, where random subsets of instances and features a...

With the advent of new loads and generation on the low voltage grid, voltage fluctuation has increased, especially in active distribution grids with a high penetration of distributed resources and a large deployment of electric vehicles. The coordination of different technologies has emerged as the best way for voltage regulation, among others, sma...

The development of novel frameworks to understand the properties of unconscious representations and how they differ from the conscious counterparts may be critical to make progress in the neuroscience of vision consciousness. Here we re-analysed data from a within-subject, high-precision, highly-sampled fMRI study (N=7) coupled with model-based rep...

p>In this paper, for the first time, a feature selection (FS) problem for an unattributed-identity multi-target regression (UIMTR) problem is presented. UIMTR is defi?ned as a multi-target regression problem where the set of target and predictor variables are undetermined, i.e., the identity of the variables is unattributed. Two forward selection ?...

p>In this paper, for the first time, a feature selection (FS) problem for an unattributed-identity multi-target regression (UIMTR) problem is presented. UIMTR is defi?ned as a multi-target regression problem where the set of target and predictor variables are undetermined, i.e., the identity of the variables is unattributed. Two forward selection ?...

p>With the advent of new loads and generation on the low voltage grid, voltage fluctuation has increased, especially in active distribution grids with a high penetration of distributed resources and a large deployment of electric vehicles. The coordination of different technologies has emerged as the best way for voltage regulation, among others, s...

There are few optimization methods that can be applied to the Hamiltonian cycle problem (HCP) on directed graphs. The Branch-and-Fix (BF) algorithm proposed by Ejov et al. (2009) can solve the HCP on this type of graphs. BF uses the idea that the HCP can be embedded in a discounted Markov decision problem and addresses this problem by solving a se...

Deep Learning has been very successful in automating the feature engineering process, widely applied for various tasks, such as speech recognition, classification, segmentation of images, time-series forecasting, among others. Deep neural networks (DNNs) incorporate the power to learn patterns through data, following an end-to-end fashion and expan...

A framework to pinpoint the scope of unconscious processing is critical to improve models of visual consciousness. Previous research observed brain signatures of unconscious processing in visual cortex, but these were not reliably identified. Further, whether unconscious contents are represented in high-level stages of the ventral visual stream and...

The Hamiltonian cycle problem consists of finding a cycle in a given graph that passes through every single vertex exactly once, or determining that this cannot be achieved. In this investigation, a graph is considered with an associated set of matrices. The entries of each of the matrix correspond to a different weight of an arc. A multi-objective...

Sampling methods are a critical step for model-based evolutionary algorithms, their goal being the generation of new and promising individuals based on the information provided by the model. Adversarial perturbations have been proposed as a way to create samples that deceive neural networks. In this paper we introduce the idea of creating adversari...

Abstract: The public procurement process plays an important role in the efficient use of public resources. In this context, the evaluation of machine learning techniques that are able to predict the award price is a relevant research topic. In this paper, the suitability of a representative set of machine learning algorithms is evaluated for this p...

The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to efficiently generate adversarial attacks, some of them relying on different theoretical justifications. Among these strategies, universal (input-agnostic) perturbations are of...

Human-machine interaction is increasingly dependent on speech communication, mainly due to the remarkable performance of Machine Learning models in speech recognition tasks. However, these models can be fooled by adversarial examples, which are inputs intentionally perturbed to produce a wrong prediction without the changes being noticeable to huma...

In many Natural Language Processing problems the combination of machine learning and optimization techniques is essential. One of these problems is the estimation of the human effort needed to improve a text that has been translated using a machine translation method. Recent advances in this area have shown that Gaussian Processes can be effective...

This work investigates different Bayesian network structure learning techniques by thoroughly studying several variants of Hybrid Multi-objective Bayesian Estimation of Distribution Algorithm (HMOBEDA), applied to the MNK Landscape combinatorial problem. In the experiments, we evaluate the performance considering three different aspects: optimizati...

Choosing the best kernel is crucial in many Machine Learning applications. Gaussian Processes are a state-of-the-art technique for regression and classification that heavily relies on a kernel function. However, in the Gaussian Processes literature, kernels have usually been either ad hoc designed, selected from a predefined set, or searched for in...

p>With the advent of smart grids, voltage fluctuation has increased, especially in active distribution networks with a high penetration of distributed energy resources and a large deployment of electric vehicles. In this context, on-load tap-changer (OLTC) distribution transformers have become a key component, mainly because they provide automatic...

p>With the advent of new loads and generation on the low voltage grid, voltage fluctuation has increased, especially in active distribution grids with a high penetration of distributed resources and a large deployment of electric vehicles. The coordination of different technologies has emerged as the best way for voltage regulation, among others, s...

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out-of-distribution inputs. In this paper, we explore the possibilities and limits of adversarial att...

With neural architecture search methods gaining ground on manually designed deep neural networks -even more rapidly as model sophistication escalates-, the research trend shifts towards arranging different and often increasingly complex neural architecture search spaces. In this conjuncture, delineating algorithms which can efficiently explore thes...

The performance of support vector machines in nonlinearly separable classification problems strongly relies on the kernel function. Toward an automatic machine learning approach for this technique, many research outputs have been produced dealing with the challenge of automatic learning of good-performing kernels for support vector machines. Howeve...

Neuroevolutionary algorithms, automatic searches of neural network structures by means of evolutionary techniques, are computationally costly procedures. In spite of this, due to the great performance provided by the architectures which are found, these methods are widely applied. The final outcome of neuroevolutionary processes is the best structu...

The goal of active aging is to promote changes in the elderly community so as to maintain an active, independent and socially-engaged lifestyle. Technological advancements currently provide the necessary tools to foster and monitor such processes. This paper reports on mid-term achievements of the European H2020 EMPATHIC project, which aims to rese...

A U-Net is a convolutional neural network mainly used for image segmentation domains such as medical image analysis. As other deep neural networks, the U-Net architecture influences the efficiency and accuracy of the network. We propose the use of a grammar-based evolutionary algorithm for the automatic design of deep neural networks for image segm...

An End-Of-Turn Detection Module (EOTD-M) is an essential component of automatic Spoken Dialogue Systems. The capability of correctly detecting whether a user’s utterance has ended or not improves the accuracy in interpreting the meaning of the message and decreases the latency in the answer. Usually, in dialogue systems, an EOTD-M is coupled with a...

Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tas...

Despite advances in the neuroscience of visual consciousness over the last decades, we still lack a framework for understanding the scope of unconscious processing and how it relates to conscious experience. Previous research observed brain signatures of unconscious contents in visual cortex, but these have not been identified in a reliable manner,...

Word-embeddings are vectorized numerical representations of words increasingly applied in natural language processing. Spaces that comprise the embedding representations can capture semantic and other relationships between the words. In this paper we show that it is possible to learn methods for word composition in semantic spaces using genetic pro...

The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to efficiently generate adversarial attacks, some of them relying on different theoretical justifications. Among these strategies, universal (input-agnostic) perturbations are of...

Centrifugation is a technique applied to assist in the freeze concentration of fruit juices and solutions. The aim of this work was to study the influence of the time–temperature parameters on the centrifugation process as a technique applied to assist in the first cycle of the freeze concentration of blueberry juice. A completely randomized 4 × 3...

The Hamiltonian cycle problem (HCP) consists of finding a cycle of length N in an N-vertices graph. In this investigation, a graph G is considered with an associated set of matrices, in which each cell in the matrix corresponds to the weight of an arc. Thus, a multi-objective variant of the HCP is addressed and a Pareto set of solutions that minimi...

The generative adversarial network (GAN) is a good example of a strong-performing, neural network-based generative model, even though it does have some drawbacks of its own. Mode collapsing and the difficulty in finding the optimal network structure are two of the most concerning issues. In this paper, we address these two issues at the same time b...

[This corrects the article DOI: 10.1098/rsos.192043.].

How the brain representation of conceptual knowledge varies as a function of processing goals, strategies and task-factors remains a key unresolved question in cognitive neuroscience. In the present functional magnetic resonance imaging study, participants were presented with visual words during functional magnetic resonance imaging (fMRI). During...

The tool-path problem has been extensively studied in manufacturing technologies, as it has a considerable impact on production time. Additive manufacturing is one of these technologies; it takes time to fabricate parts, so the selection of optimal tool-paths is critical. This research analyzes the tool-path problem in the direct energy deposition...

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible but malicious perturbations to natural inputs. These altered inputs are known in the literature as adversarial example...

The neural network research field is still producing novel and improved models which continuously outperform their predecessors. However, a large portion of the best-performing architectures are still fully hand-engineered by experts. Recently, methods that automatize the search for optimal structures have started to reach the level of state-of-the...

Human-machine interaction is increasingly dependent on speech communication. Machine Learning models are usually applied to interpret human speech commands. However, these models can be fooled by adversarial examples, which are inputs intentionally perturbed to produce a wrong prediction without being noticed. While much research has been focused o...

In many Natural Language Processing problems the combination of machine learning and optimization techniques is essential. One of these problems is estimating the effort required to improve, under direct human supervision, a text that has been translated using a machine translation method. Recent developments in this area have shown that Gaussian P...

The optimization of massively multi-modal functions is a challenging task, particularly for problems where the search space can lead the optimization process to local optima. While evolutionary algorithms have been extensively investigated for these optimization problems, Bayesian Optimization algorithms have not been explored to the same extent. I...

Text Classification is one of the tasks of Natural Language Processing (NLP). In this area, Graph Convolutional Networks (GCN) has achieved values higher than CNN's and other related models. For GCN, the metric that defines the correlation between words in a vector space plays a crucial role in the classification because it determines the weight of...

Adversarial examples are inputs subtly perturbed to produce a wrong prediction in machine learning models, while remaining perceptually similar to the original input. To find adversarial examples, some attack strategies rely on linear approximations of different properties of the models. This opens a number of questions related to the accuracy of s...

Bayesian Optimization has been widely used along with Gaussian Processes for solving expensive-to-evaluate black-box optimization problems. Overall, this approach has shown good results, and particularly for parameter tuning of machine learning algorithms. Nonetheless, Bayesian Optimization has to be also configured to achieve the best possible per...

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied in the image domain, classification tasks in the audio domain have received less attention. In this paper we...

How the brain representation of conceptual knowledge vary as a function of processing goals remains unclear. We hypothesized that the brain representation of semantic categories is shaped by the depth of processing. Participants were presented with visual words during functional MRI. During shallow processing, participants had to read the items. Du...