Search

We analize the Mexican peso-US dollar exchange parity the volatility using three models in order to evaluate the exchange rate risk performance and the these models capability of modeling such risk. The period June 21st, 2017 to June 21st, 2022 is marked by singular events that pressed this exchange rate parity, making it of great interest to study the tools that can be used to measure this uncertainty besides the study of the exchange rate uncertainty itself. The arrival of a leftwing politician to the presidency was an unprecedented event. At the beginning of 2020 the price war in the oil market and the emergence of the COVID-19 pandemic had important effects in the world economy. Finally, the war in Ukraine added pressures to the international trade of raw materials, inducing an inflationary episode with bad expectations about the economic performance around the world. The exchange rate scenarios posed by the aforesaid events provide us with a natural context to test which of the posited volatility models offers a better fit. Unanimously, the results under the three models suggest that during the first year of the President López Obrador period the exchange rate uncertainty was reduced compared to previous levels, returning again to those minor levels after the forced closure of economic activities due to the emergence of COVID-19, even though the exchange fluctuation band has been slightly higher than before the pandemic and the war on East Europe. [ABSTRACT FROM AUTHOR]

Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher’s discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task. [ABSTRACT FROM AUTHOR]

Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class overlap, separability or boundary shapes, as well as group morphology. Many techniques can transform the data in order to find better features, but few focus on specifically reducing data complexity. Most data transformation methods mainly treat the dimensionality aspect, leaving aside the available information within class labels which can be useful when classes are somehow complex. This paper proposes an autoencoder-based approach to complexity reduction, using class labels in order to inform the loss function about the adequacy of the generated variables. This leads to three different new feature learners, Scorer, Skaler and Slicer. They are based on Fisher’s discriminant ratio, the Kullback-Leibler divergence and least-squares support vector machines, respectively. They can be applied as a preprocessing stage for a binary classification problem. A thorough experimentation across a collection of 27 datasets and a range of complexity and classification metrics shows that class-informed autoencoders perform better than 4 other popular unsupervised feature extraction techniques, especially when the final objective is using the data for a classification task. [ABSTRACT FROM AUTHOR]

Despite technological advances in the world, antimicrobial resistance against Mycobacterium tuberculosis represents a great threat to public health. Worldwide, 20% of tuberculosis cases are multidrug-resistant, and the number of patients continues to increase day after day. The successful treatment of tuberculosis has become a great challenge for global health according to the World Health Organization. This review aims to give a general overview of tuberculosis, including its history, generalities, epidemiology, and treatment, and to give a broader review of new treatment proposals, reviewing their sensitivity, specificity, and reduced numbers of side effects. PubMed, Google Scholar, Elsevier, and EBSCOhost were used to obtain the main articles describing the research conducted on new drugs to treat multidrug-resistant tuberculosis and extensively drug-resistant tuberculosis. The clinical trials for the new drugs used to treat extensively drug-resistant tuberculosis demonstrated good therapeutic regimens and compared the new drugs to identify which of them had more efficacy and less toxicity. The new drugs developed to treat extensively drugresistant tuberculosis that were effective in 85%-90% of patients were bedaquiline, pretomanid, and linezolid. [ABSTRACT FROM AUTHOR]

To estimate the performance, efficacy, modes of operation, hydrodynamic instabilities, and methodologies for harnessing energy from the pump as turbine (PAT), it is necessary to characterize these hydraulic turbomachines in all their modes of operation using an experimental test rig that simulates actual operating conditions. In this process, the characteristic curve of four quadrants of a turbomachine is constructed, especially its five modes: pump mode, brake pump mode, turbine mode, brake turbine mode, and reverse pump mode. In addition, with dynamic sensors installed in the pump volute, it is possible to know the hydrodynamic phenomena within PAT, finding its average behavior and frequency response, which is a tool for diagnosing the machine's condition. [ABSTRACT FROM AUTHOR]

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning. This weak point is exacerbated by the inaccessibility of data in federated learning, which makes the protection against adversarial attacks harder and evidences the need to furtherance the research on defence methods to make federated learning a real solution for safeguarding data privacy. In this paper, we present an extensive review of the threats of federated learning, as well as as their corresponding countermeasures, attacks versus defences. This survey provides a taxonomy of adversarial attacks and a taxonomy of defence methods that depict a general picture of this vulnerability of federated learning and how to overcome it. Likewise, we expound guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Besides, we carry out an extensive experimental study from which we draw further conclusions about the behaviour of attacks and defences and the guidelines for selecting the most adequate defence method according to the category of the adversarial attack. Finally, we present our learned lessons and challenges. • We claim that adversarial attacks are a significant challenge in federated learning. • We propose taxonomies of adversarial attacks and defences in federated learning. • We conduct a wide experimental study the results of which support our claim. • We define guidelines for selecting a proper defence method according to the attack. • We stand out a set of lessons learnt, open challenges and final conclusions. [ABSTRACT FROM AUTHOR]

In large-scale group decision making (LSGDM), appropriate clustering analysis is important to consensus reaching since it can reduce the interactive complexity among individuals. According to the traditional clustering method, a conflict may arise between the consensus reaching levels and total adjustment costs within clusters when individuals have different unit adjustment cost, which reflects their willingness to make concessions. Since this conflict may aggravate the consensus complexity, we propose a new $K$ -means clustering method that considers both preferences and the preference adjustment cost. The preference adjustment cost is attached to preferences with a parameter that can be determined by balancing this conflict. Because of such conflict, the proposed clustering algorithm can improve the similarity of intracluster individuals on the preference adjustment cost by offsetting some acceptable consensus reaching levels within clusters. According to the proposed clustering algorithm, individuals who have both similar preferences and adjustment willingness are classified into the same clusters. In this way, the moderator can provide similar compensation strategies for intracluster individuals, which will decrease the adjustment complexity. A practical case study of team construction examines the application of the proposed algorithm, and the related comparative analysis shows that it is convenient for managers to persuade individuals to reach a consensus under the improved clustering results. [ABSTRACT FROM AUTHOR]

Understanding black box models has become paramount as systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its application in real-world scenarios and addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. We aim to develop a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 28 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. [ABSTRACT FROM AUTHOR]

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domain experts. In contrast, symbolic AI systems that convert concepts into rules or symbols – such as knowledge graphs – are easier to explain. However, they present lower generalization and scaling capabilities. A very important challenge is to fuse DL representations with expert knowledge. One way to address this challenge, as well as the performance-explainability trade-off is by leveraging the best of both streams without obviating domain expert knowledge. In this paper, we tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph. We present the eXplainable Neural-symbolic learning (X-NeSyL) methodology, designed to learn both symbolic and deep representations, together with an explainability metric to assess the level of alignment of machine and human expert explanations. The ultimate objective is to fuse DL representations with expert domain knowledge during the learning process so it serves as a sound basis for explainability. In particular, X-NeSyL methodology involves the concrete use of two notions of explanation, both at inference and training time respectively: (1) EXPLANet : Expert-aligned eXplainable Part-based cLAssifier NETwork Architecture, a compositional convolutional neural network that makes use of symbolic representations, and (2) SHAP-Backprop , an explainable AI-informed training procedure that corrects and guides the DL process to align with such symbolic representations in form of knowledge graphs. We showcase X-NeSyL methodology using MonuMAI dataset for monument facade image classification, and demonstrate that with our approach, it is possible to improve explainability at the same time as performance. • EXplainable Neural-symbolic Learning methodology fuses deep learning and symbolic representations. • EXPLANet's compositional part-based object detection and classification outperforms regular classification. • SHAP-Backprop aligns model output with expert knowledge in a knowledge graph. • SHAP Graph Edit Distance quantifies the alignment between a knowledge graph and neural representations. • X-NeSyL shows it is possible to improve over both explainability and performance. [ABSTRACT FROM AUTHOR]

In computing with words, it has been stressed that words mean different things for different people, which entails that decision makers (DMs) have personalized individual semantics (PISs) attached to linguistic expressions in linguistic group decision making (GDM). In particular, the PISs of DMs are not fixed, and they will be changing during the consensus building process, which indicates the necessary of continual PIS learning. Therefore, in this article, we propose a continual PIS-learning-based consensus approach in linguistic GDM. Specifically, a continual PIS learning model with the consistency-driven methodology is proposed to update the PISs taking into account all the linguistic preference data given by DMs during the consensus process. Then, the consensus measurement and feedback recommendation based on PIS are developed to detect the consensus process. Finally, numerical examples and simulation analysis are presented to illustrate and justify the use of the continual PIS-learning-based consensus approach. [ABSTRACT FROM AUTHOR]

Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet. This paper presents TimeSpec4LULC 10.5281/zenodo.5913554; , a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500 m resolution, from 2000 to 2021, and was annotated using spatial–temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE). The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial–temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8 d temporal granularity into monthly composites; (3) merging Terra + Aqua data into a combined time series; and (4) extracting, at the pixel level, 6 076 531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial–temporal consistency across LULC products, temporal data availability, and the global human modification index. A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe. To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping. [ABSTRACT FROM AUTHOR]

Image segmentation is an important issue in many industrial processes, with high potential to enhance the manufacturing process derived from raw material imaging. For example, metal phases contained in microstructures yield information on the physical properties of the steel. Existing prior literature has been devoted to develop specific computer vision techniques able to tackle a single problem involving a particular type of metallographic image. However, the field lacks a comprehensive tutorial on the different types of techniques, methodologies, their generalizations and the algorithms that can be applied in each scenario. This paper aims to fill this gap. First, the typologies of computer vision techniques to perform the segmentation of metallographic images are reviewed and categorized in a taxonomy. Second, the potential utilization of pixel similarity is discussed by introducing novel deep learning-based ensemble techniques that exploit this information. Third, a thorough comparison of the reviewed techniques is carried out in two openly available real-world datasets, one of them being a newly published dataset directly provided by ArcelorMittal, which opens up the discussion on the strengths and weaknesses of each technique and the appropriate application framework for each one. Finally, the open challenges in the topic are discussed, aiming to provide guidance in future research to cover the existing gaps. [Display omitted] • We create a metallography dataset from additive manufacturing of steels (MetalDAM). • We provide an updated taxonomy of segmentation methods. • We propose a new DL-based ensemble specialized in the semantic segmentation task. • We compare state-of-the-art models and the new ensembles with UHCS and MetalDAM. • We present a thorough analysis of the current difficulties and challenges. [ABSTRACT FROM AUTHOR]

Most applications of Artificial Intelligence (AI) are designed for a confined and specific task. However, there are many scenarios that call for a more general AI, capable of solving a wide array of tasks without being specifically designed for them. The term General Purpose Artificial Intelligence Systems (GPAIS) has been defined to refer to these AI systems. To date, the possibility of an Artificial General Intelligence, powerful enough to perform any intellectual task as if it were human, or even improve it, has remained an aspiration, fiction, and considered a risk for our society. Whilst we might still be far from achieving that, GPAIS is a reality and sitting at the forefront of AI research. This work discusses existing definitions for GPAIS and proposes a new definition that allows for a gradual differentiation among types of GPAIS according to their properties and limitations. We distinguish between closed-world and open-world GPAIS, characterising their degree of autonomy and ability based on several factors such as adaptation to new tasks, competence in domains not intentionally trained for, ability to learn from few data, or proactive acknowledgement of their own limitations. We then propose a taxonomy of approaches to realise GPAIS, describing research trends such as the use of AI techniques to improve another AI (commonly referred to as AI-powered AI) or (single) foundation models. As a prime example, we delve into generative AI (GenAI), aligning them with the terms and concepts presented in the taxonomy. Similarly, we explore the challenges and prospects of multi-modality, which involves fusing various types of data sources to expand the capabilities of GPAIS. Through the proposed definition and taxonomy, our aim is to facilitate research collaboration across different areas that are tackling general purpose tasks, as they share many common aspects. Finally, with the goal of providing a holistic view of GPAIS, we discuss the current state of GPAIS, its prospects, implications for our society, and the need for regulation and governance of GPAIS to ensure their responsible and trustworthy development. • Presents a holistic view of General Purpose Artificial Intelligence Systems. • Consolidates a definition for general-purpose AI based on their degree of autonomy. • Breaking it down onto a taxonomy of approaches to build general-purpose AI systems. • A close look into Generative AI as a prime example of general-purpose AI systems. • Discusses open challenges, implications for our society and need for regulation. [ABSTRACT FROM AUTHOR]

Experts from different domains have resorted to machine learning techniques to produce explainable models that support decision-making. Among existing techniques, decision trees have been useful in many application domains for classification. Decision trees can make decisions in a language that is closer to that of the experts. Many researchers have attempted to create better decision tree models by improving the components of the induction algorithm. One of the main components that have been studied and improved is the evaluation measure for candidate splits. In this article, we introduce a tutorial that explains decision tree induction. Then, we present an experimental framework to assess the performance of 21 evaluation measures that produce different C4.5 variants considering 110 databases, two performance measures, and 10× 10-fold cross-validation. Furthermore, we compare and rank the evaluation measures by using a Bayesian statistical analysis. From our experimental results, we present the first two performance rankings in the literature of C4.5 variants. Moreover, we organize the evaluation measures into two groups according to their performance. Finally, we introduce meta-models that automatically determine the group of evaluation measures to produce a C4.5 variant for a new database and some further opportunities for decision tree models. [ABSTRACT FROM AUTHOR]

• A democratic consensus reaching process (DCRP) for MpMcLSDM is proposed. • A clustering method that considers both the opinion similarity and self-concern similarity of DM is presented. • A consensus contribution-based dynamic interactive weight updating method is given. • A compromise degree-based consensus feedback strategy is developed. Consensus reaching is a key issue in group decision-making, because conflicts of interest among groups are common. Democratic consensus refers to achieve a soft consensus among collective as well as ensure the effective participation and satisfaction of individuals. Multi-person multi-criteria large scale decision making (MpMcLSDM) usually involves a huge number of decision makers (DMs/participants), and different DMs usually have different interests. Thus, how to effectively manage individuals to promote democratic consensus is a current research challenge. To do that, this research develops a democratic consensus reaching process (DCRP) for MpMcLSDM problems. In the proposed approach, a clustering method that considers both the opinion similarity and individual concern similarity of DM is firstly given to decrease the complexity of MpMcLSDM issues. Subsequently, we propose to assign equal initial weight to each cluster to protect the interests of minorities. Meanwhile, a consensus contribution-based dynamic interactive weight updating method is implemented in the DCRPs to promote a high level of democratic consensus. Besides, a compromise degree-based consensus feedback strategy is developed to improve the efficiency of the DCRPs. The proposed feedback mechanism effectively considers the individual concern and adjustment willingness of DMs in the DCRPs. Finally, a case study and some comparisons are given to show the effectiveness and innovation of this research. [ABSTRACT FROM AUTHOR]

Land Use and Land Cover (LULCs) mapping and change detection are of paramount importance to understand the distribution and effectively monitor the dynamics of the Earth's system. An unexplored way to create global LULC maps is by building good quality LULC-models based on state-of-the-art deep learning networks. Building such models requires large global good quality time series LULC datasets, which are not available yet. This paper presents TimeSpec4LULC (Khaldi et al., 2021), a smart open-source global dataset of multi-Spectral Time series for 29 LULC classes. TimeSpec4LULC was built based on the 7 spectral bands of MODIS sensor at 500 m resolution from 2002 to 2021, and was annotated using a spatial agreement across the 15 global LULC products available in Google Earth Engine. The 19-year monthly time series of the seven bands were created globally by: (1) applying different spatio-temporal quality assessment filters on MODIS Terra and Aqua satellites, (2) aggregating their original 8-day temporal granularity into monthly composites, (3) merging their data into a Terra+Aqua combined time series, and (4) extracting, at the pixel level, 11.85 million time series for the 7 bands along with a set of metadata about geographic coordinates, country and departmental divisions, spatio-temporal consistency across LULC products, temporal data availability, and the global human modification index. To assess the annotation quality of the dataset, a sample of 100 pixels, evenly distributed around the world, from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing and evaluating various machine learning models, including deep learning networks, to perform global LULC mapping and change detection. [ABSTRACT FROM AUTHOR]

To date, a large number of consensus reaching processes (CRPs) have been reported in group decision making (GDM). Trust relationships should be an essential element in interactions among a group of individuals, leading to the evolution of individuals’ preferences. Therefore, in this article, we present a trust relationships CRP with a feedback mechanism which consists of two approaches of facilitating consensus reaching: 1) the leader-based preference adjustment and 2) the trust relationships improvement. In the trust relationships CRP, we build a bridge between opinion dynamics and GDM to highlight the role of the leaders and trust relationships improvements in the GDM problems. Furthermore, we present a new strategic manipulation issue, called trust relationship manipulation, and discuss some clique-based strategies to manipulate trust relationships to obtain the desired ranking of the alternatives in the GDM problems. Finally, the detailed simulation experiments are proposed to justify our proposal. [ABSTRACT FROM AUTHOR]

The present work reports iron tungstate (FeWO 4) nanostructures with reduced graphene oxide (rGO) as a novel anode material for enhancing the electrochemical properties of asymmetric supercapacitors. The FeWO 4 -rGO composite nanostructures were successfully synthesized by the one-pot sonochemical method. The synthesized nanocomposites crystal structure and phase purity were investigated using the powder X-ray diffraction (XRD) technique. The Fourier transform infrared (FT-IR) spectrograms demonstrate the presence of functional groups in the composite. The composite's morphology was examined using the high-resolution transmission electron microscopy (HR-TEM) and the field emission scanning electron microscopy (FE-SEM), and it was observed that the FeWO 4 nanostructures were uniformly distributed on the reduced graphene oxide surface. The cyclic voltammetry (CV), galvanostatic charge-discharge (GCD), and electrochemical impedance spectroscopy (EIS) analyses were used to evaluate the electrochemical performance. After 5000 cycles at 10 mA cm− 2, the FeWO 4 -rGO composite achieved a better rate of efficiency and outstanding cycling performance, with capacitance retained at 68% and 77.8%, respectively. In 1 M Na 2 SO 4 , an asymmetric device (CuCo 2 O 4 //FeWO 4 -rGO composite) achieved a high energy density of 21.5 W.h Kg−1 and a power density of 147 W Kg−1. In the FeWO 4 -rGO nanocomposite, the reduced graphene oxide could enhance the conductivity and the free diffusion processes for the quick ion transport and easy ion access to the storage sites. The obtained results indicated that the FeWO 4 -rGO nanocomposite could be a good anode electrode material for the next-generation energy storage applications. [Display omitted] • FeWO 4 nanostructures with rGO are synthesized by sonochemical synthesis. • FeWO 4 -rGO composite exhibited a specific capacitance of 414 Fg−1 at a current density of 1 mA cm−2. • FeWO 4 -rGO composite delivered an improved rate capability of 68% and excellent cycling stability of 77.8%. • An asymmetric device CuCO 2 O 4 // FeWO 4 -rGO device provided a high energy density. [ABSTRACT FROM AUTHOR]

Anomaly detection aims to identify observations that differ significantly from the majority of the data. Time series, which are data with a temporal component, is often used for anomaly detection. Identifying anomalies is not perfect and may produce many false positives, which labels standard data as anomalous. In this context, false positive mitigation is the task of reducing the number of false positives tagged by the anomaly detector, and thus both problems are closely linked. Moreover, current techniques for false positive mitigation are ad-hoc solutions for specific data sets. In this paper, we propose a novel two-stage methodology for Multivariate Anomaly Detection for Time Series and False Positive Mitigation, namely F A D F P M methodology, which creates the fusion of two learning models. The first stage is a multivariate anomaly detection stage. The second stage consists of training a new classifier on the false and true positives from the anomaly detector, which refines the observations labeled as anomalous by the anomaly detector to obtain more accurate and higher-quality results. Experiments using two benchmark data sets, as well as a real-world case study have shown the performance and validity of the proposal. • Proposed methodology decreases impact from FPs in anomaly detection. • A thorough comparison with latest SOA methods is performed. • We also provide a series of hints for applying the methodology. • High sensitivity methods are more benefited from the proposal. • A real-world case of study provided by ArcelorMIttal is analyzed. [ABSTRACT FROM AUTHOR]

Due to their high adaptability to varied settings and effective optimization algorithm, Convolutional Neural Networks (CNNs) have set the state-of-the-art on image processing jobs for the previous decade. CNNs work in a sequential fashion, alternating between extracting significant features from an input image and aggregating these features locally through "pooling" functions, in order to produce a more compact representation. Functions like the arithmetic mean or, more typically, the maximum are commonly used to perform this downsampling operation. Despite the fact that many studies have been devoted to the development of alternative pooling algorithms, in practice, "max-pooling" still equals or exceeds most of these possibilities, and has become the standard for CNN construction. In this paper we focus on the properties that make the maximum such an efficient solution in the context of CNN feature downsampling and propose its replacement by grouping functions, a family of functions that share those desirable properties. In order to adapt these functions to the context of CNNs, we present (a , b) -grouping functions, an extension of grouping functions to work with real valued data. We present different construction methods for (a , b) -grouping functions, and demonstrate their empirical applicability for replacing max-pooling by using them to replace the pooling function of many well-known CNN architectures, finding promising results. • Grouping pooling generalizes maximum pooling while considering all inputs. • Aggregation functions extended to a real domain (a, b) can act as pooling operator. • Different methods for constructing (a, b)-grouping functions are presented. • (a, b)-grouping poolings improve the gradient flow of max-pooling. [ABSTRACT FROM AUTHOR]

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective. However, attaining truly trustworthy AI concerns a wider vision that comprises the trustworthiness of all processes and actors that are part of the system's life cycle, and considers previous aspects from different lenses. A more holistic vision contemplates four essential axes: the global principles for ethical use and development of AI-based systems, a philosophical take on AI ethics, a risk-based approach to AI regulation, and the mentioned pillars and requirements. The seven requirements (human agency and oversight; robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental wellbeing; and accountability) are analyzed from a triple perspective: What each requirement for trustworthy AI is, Why it is needed, and How each requirement can be implemented in practice. On the other hand, a practical approach to implement trustworthy AI systems allows defining the concept of responsibility of AI-based systems facing the law, through a given auditing process. Therefore, a responsible AI system is the resulting notion we introduce in this work, and a concept of utmost necessity that can be realized through auditing processes, subject to the challenges posed by the use of regulatory sandboxes. Our multidisciplinary vision of trustworthy AI culminates in a debate on the diverging views published lately about the future of AI. Our reflections in this matter conclude that regulation is a key for reaching a consensus among these views, and that trustworthy and responsible AI systems will be crucial for the present and future of our society. • A holistic vision of trustworthy AI with principles for ethical use and development. • A philosophical reflection on AI Ethics. • An analysis of regulatory efforts around trustworthy AI focused on the European AI Act. • An examination of the fundamental pillars and requirements for trustworthy AI. • A definition of responsible AI systems and the role of regulatory sandboxes. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model's decision-making. Thus, the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen. XAI has become a popular research subject within the AI field in recent years. Existing survey papers have tackled the concepts of XAI, its general terms, and post-hoc explainability methods but there have not been any reviews that have looked at the assessment methods, available tools, XAI datasets, and other related aspects. Therefore, in this comprehensive study, we provide readers with an overview of the current research and trends in this rapidly emerging area with a case study example. The study starts by explaining the background of XAI, common definitions, and summarizing recently proposed techniques in XAI for supervised machine learning. The review divides XAI techniques into four axes using a hierarchical categorization system: (i) data explainability, (ii) model explainability, (iii) post-hoc explainability, and (iv) assessment of explanations. We also introduce available evaluation metrics as well as open-source packages and datasets with future research directions. Then, the significance of explainability in terms of legal demands, user viewpoints, and application orientation is outlined, termed as XAI concerns. This paper advocates for tailoring explanation content to specific user types. An examination of XAI techniques and evaluation was conducted by looking at 410 critical articles, published between January 2016 and October 2022, in reputed journals and using a wide range of research databases as a source of information. The article is aimed at XAI researchers who are interested in making their AI models more trustworthy, as well as towards researchers from other disciplines who are looking for effective XAI methods to complete tasks with confidence while communicating meaning from data. • A novel four-axis framework to examine a model for robustness and explainability. • Formulation of research questions at each axis and its corresponding taxonomy. • Discussion of different explainability assessment methods. • A novel methodological workflow for determining the model and explainability criteria. • Revisited discussion on challenges and future directions of XAI and Trustworthy AI. [ABSTRACT FROM AUTHOR]

There exist a high demand to provide explainability to artificial intelligence systems, where decision making models are included. This paper focuses on crowd decision making using natural language evaluations from social media with the aim to provide explainability. We present the Explainable Crowd Decision Making based on Subgroup Discovery and Attention Mechanisms (ECDM-SDAM) methodology as an a posteriori explainable process that captures the wisdom of crowds that is naturally provided in social media opinions. It extracts the opinions from social media texts using a deep learning based sentiment analysis approach called Attention based Sentiment Analysis Method. The methodology includes a backward process that provides explanations to justify its sense-making procedure by applying mainly the attention mechanism on texts and subgroup discovery on opinions. We evaluate the methodology in the real case study of the TripR-2020Large dataset for restaurant choice. The results show that the ECDM-SDAM methodology provides easy understandable explanations that elucidates the key reasons that support the output of the decision process. • Explainability in decision making is essential to increase its use and understanding. • Attention mechanisms and subgroup discovery can generate explainable decision making. • We propose a methodology that offers explanations of its internal decision mechanism. • The proposed methodology captures the wisdom of crowds from social media. • Natural language with sentiment analysis and deep learning enriches expert evaluation. [ABSTRACT FROM AUTHOR]

Modern machine learning algorithms excel in a great variety of tasks, but at the same time, it is also known that those complex models need to deal with uncertainty from different sources. Consequently, understanding if the model is indeed making accurate predictions or simply guessing at random is not trivial, and measuring the confidence bounds becomes very important. Bayesian machine learning seems to provide the solution, however, many of the state-of-the-art Bayesian algorithms use rigid parametric representations of the uncertainty where the learning process depends on the gradient of a predefined cost function. In this article, a new gradient-free training algorithm based on Approximate Bayesian Computation by Subset Simulation is proposed, where the likelihood function and the weights are defined by non-parametric formulations, resulting in a flexible and fairer representation of the uncertainty. The experiments, specially the engineering case study on composite materials subject to fatigue damage, show the ability of the proposed algorithm to consistently reach accurate predictions while avoiding gradient related instabilities, and most importantly, it provides a realistic and coherent quantification of the uncertainty represented by confidence bounds. All this may lead to a reduction of safety factors in engineering problems, and in general, allows us to make well-informed decisions in situations with a high degree of uncertainty and risk. A comparison with the state-of-the-art Bayesian Neural Networks is also carried out. • Neural networks trained with approximate Bayesian computation. • Accurate and flexible representation of the uncertainty in the observed data. • Stability of predictions thanks to the gradient-free nature of the algorithm. • Non-parametric weights and likelihood function provide adaptability to data. • Appropriate when decisions are dependent on the level of uncertainty. [ABSTRACT FROM AUTHOR]