Search

Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex and opaque machine learning (ML) models. Despite the development of a multitude of methods to explain the decisions of black-box classifiers in recent years, these tools are seldomly used beyond visualization purposes. Only recently, researchers have started to employ explanations in practice to actually improve models. This paper offers a comprehensive overview over techniques that apply XAI practically to obtain better ML models, and systematically categorizes these approaches, comparing their respective strengths and weaknesses. We provide a theoretical perspective on these methods, and show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning, among others. We further discuss potential caveats and drawbacks of these methods. We conclude that while model improvement based on XAI can have significant beneficial effects even on complex and not easily quantifiable model properties, these methods need to be applied carefully, since their success can vary depending on a number of factors, such as the model and dataset used, or the employed explanation method. [Display omitted] • We show how and why XAI improves several model properties in toy experiments. • We develop a unifying theoretical framework for XAI-based model improvement. • We extensively review and discuss existing approaches that use XAI to improve models. • We provide experiment-supported practical recommendations for XAI-based augmentation. [ABSTRACT FROM AUTHOR]

An in-depth understanding of uncertainty is the first step to making effective decisions under uncertainty. Machine/deep learning (ML/DL) has been hugely leveraged to solve complex problems involved with processing high-dimensional data. However, reasoning and quantifying different uncertainties to achieve effective decision-making have been much less explored in ML/DL than in other Artificial Intelligence (AI) domains. In particular, belief/evidence theories have been studied in Knowledge representation and reasoning (KRR) since the 1960s to reason and measure uncertainties to enhance decision-making effectiveness. Based on our in-depth literature review, only a few studies have leveraged mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty. Our present survey paper discusses major belief theories and their core ideas dealing with uncertainty causes and types and quantifying them, along with the discussions of their applicability in ML/DL. Particularly, we discuss three main approaches leveraging belief theories in Deep Neural Networks (DNNs), including Evidential DNNs, Fuzzy DNNs, and Rough DNNs, in terms of their uncertainty causes, types, and quantification methods along with their applicability in diverse problem domains. Through an in-depth understanding of the extensive survey on this topic, we discuss insights, lessons learned, limitations of the current state-of-the-art bridging belief theories and ML/DL, and future research directions. This paper conducts an extensive survey by bridging belief theories and deep learning in reasoning and quantifying uncertainty to help researchers initiate uncertainty and decision-making research. • Identifying the causes and types of uncertainty in various belief models. • Uncertainty reasoning and quantification of belief models for decision-making. • Applying uncertainty quantification of belief models into deep learning. • Comparing uncertainty consideration in belief models and deep learning. • Insights, lessons learned, limitations, and future research directions. [ABSTRACT FROM AUTHOR]

Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain knowledge (e.g. Clever Hans effects) have been identified as a starting point for improving faulty models. However, it is less clear what to do when the user and the explanation agree. In this paper, we demonstrate that acceptance of explanations by the user is not a guarantee for a machine learning model to be robust against Clever Hans effects, which may remain undetected. Such hidden flaws of the model can nevertheless be mitigated, and we demonstrate this by contributing a new method, Explanation-Guided Exposure Minimization (EGEM), that preemptively prunes variations in the ML model that have not been the subject of positive explanation feedback. Experiments demonstrate that our approach leads to models that strongly reduce their reliance on hidden Clever Hans strategies, and consequently achieve higher accuracy on new data. • Explainable AI may not detect all Clever Hans effects in practical ML scenarios. • Hidden Clever Hans effects can be mitigated using Exposure Minimization. • We propose a solution in the form of a soft-pruning scheme on network activations. • We demonstrate the practical benefits of our approach on image and text data. [ABSTRACT FROM AUTHOR]

Nowadays, Artificial intelligence (AI), combined with the digitalization of healthcare, can lead to substantial improvements in Patient Care, Disease Management, Hospital Administration, and supply chain effectiveness. Among predictive analytics tools, time series forecasting represents a central task to support healthcare management in terms of bookings and medical services predictions. In this context, the development of flexible frameworks to provide robust and reliable predictions became a central point in this healthcare innovation process. This paper presents and discusses a multi-source time series fusion and forecasting framework relying on Deep Learning. By combining weather, air-quality and medical bookings time series through a feature compression stage which preserves temporal patterns, the prediction is provided through a flexible ensemble technique based on machine learning models and a hybrid neural network. The proposed system is able to predict the number of bookings related to a specific medical examination for a 7-days horizon period. To assess the proposed approach's effectiveness, we rely on time series extracted from a real dataset of administrative e-health records provided by the Campania Region health department, in Italy. • We propose a multi-source time-series fusion methodology relying on Deep Learning. • We design a robust framework for daily 7-days-horizon predictions. • We assess the proposed approach on a real medical bookings dataset. [ABSTRACT FROM AUTHOR]

Abstract: Biologically-inspired methods such as evolutionary algorithms and neural networks are proving useful in the field of information fusion. Artificial immune systems (AISs) are a biologically-inspired approach which take inspiration from the biological immune system. Interestingly, recent research has shown how AISs which use multi-level information sources as input data can be used to build effective algorithms for realtime computer intrusion detection. This research is based on biological information fusion mechanisms used by the human immune system and as such might be of interest to the information fusion community. The aim of this paper is to present a summary of some of the biological information fusion mechanisms seen in the human immune system, and of how these mechanisms have been implemented as AISs. [Copyright &y& Elsevier]

In this paper we develop a Potts spin neural clustering method for clustering belief functions based on attracting and conflicting metalevel evidence. Such clustering is useful when the belief functions concern multiple events, and all belief functions are mixed up. The clustering process is used as the means for separating the belief functions into clusters that should be handled independently. A measure for the adequacy of a partitioning of all belief functions is derived and mapped onto the neural network in order to obtain fast clustering. A comparison of classification error rate between using conflicting metalevel evidence only and both conflicting and attracting metalevel evidence demonstrates a significant reduction in classification error rate when using both. [Copyright &y& Elsevier]