Knowledge bases are employed in a variety of applications, from natural language processing to semantic web search; alas, in practice, their usefulness is hurt by their incompleteness. To address this issue, several techniques aim at performing knowledge base completion, of which embedding models are efficient, attain state-of-the-art accuracy, and eliminate the need for feature engineering. However, embedding models predictions are notoriously hard to interpret. In this work, we propose model-agnostic methods that allow one to interpret embedding models by extracting weighted Horn rules from them. More specifically, we show how the so-called \"pedagogical techniques\", from the literature on neural networks, can be adapted to take into account the large-scale relational aspects of knowledge bases, and show experimentally their strengths and weaknesses. / Bases de conhecimento apresentam diversas aplicações, desde processamento de linguagem natural a pesquisa semântica da web; contudo, na prática, sua utilidade é prejudicada por não serem totalmente completas. Para solucionar esse problema, diversas técnicas focam em completar bases de conhecimento, das quais modelos de embedding são eficientes, atingem estado da arte em acurácia, e eliminam a necessidade de fazer-se engenharia de características dos dados de entrada. Entretanto, as predições dos modelos de embedding são notoriamente difíceis de serem interpretadas. Neste trabalho, propomos métodos agnósticos a modelo que permitem interpretar modelos de embedding através da extração de regras Horn ponderadas por pesos dos mesmos. Mais espeficicamente, mostramos como os chamados \"métodos pedagógicos\", da literatura de redes neurais, podem ser adaptados para lidar com os aspectos relacionais e de larga escala de bases de conhecimento, e mostramos experimentalmente seus pontos fortes e fracos.

Knowledge bases are employed in a variety of applications, from natural language processing to semantic web search; alas, in practice, their usefulness is hurt by their incompleteness. To address this issue, several techniques aim at performing knowledge base completion, of which embedding models are efficient, attain state-of-the-art accuracy, and eliminate the need for feature engineering. However, embedding models predictions are notoriously hard to interpret. In this work, we propose model-agnostic methods that allow one to interpret embedding models by extracting weighted Horn rules from them. More specifically, we show how the so-called \"pedagogical techniques\", from the literature on neural networks, can be adapted to take into account the large-scale relational aspects of knowledge bases, and show experimentally their strengths and weaknesses. / Bases de conhecimento apresentam diversas aplicações, desde processamento de linguagem natural a pesquisa semântica da web; contudo, na prática, sua utilidade é prejudicada por não serem totalmente completas. Para solucionar esse problema, diversas técnicas focam em completar bases de conhecimento, das quais modelos de embedding são eficientes, atingem estado da arte em acurácia, e eliminam a necessidade de fazer-se engenharia de características dos dados de entrada. Entretanto, as predições dos modelos de embedding são notoriamente difíceis de serem interpretadas. Neste trabalho, propomos métodos agnósticos a modelo que permitem interpretar modelos de embedding através da extração de regras Horn ponderadas por pesos dos mesmos. Mais espeficicamente, mostramos como os chamados \"métodos pedagógicos\", da literatura de redes neurais, podem ser adaptados para lidar com os aspectos relacionais e de larga escala de bases de conhecimento, e mostramos experimentalmente seus pontos fortes e fracos.

An in-vehicle intrusion detection system (IV-IDS) is one of the protection mechanisms used to detect cyber attacks on electric or autonomous vehicles where anomaly-based IDS solution have better potential at detecting the attacks especially zero-day attacks. Generally, the IV-IDS generate false alarms (falsely detecting normal data as attacks) because of the difficulty to differentiate between normal and attack data. It can lead to undesirable situations, such as increased laxness towards the system, or uncertainties in the event-handling following a generated alarm. With the help of sophisticated Artificial Intelligence (AI) models, the IDS improves the chances of detecting attacks. However, the use of such a model comes at the cost of decreased interpretability, a trait that is argued to be of importance when ascertaining various other valuable desiderata, such as a model’s trust, causality, and robustness. Because of the lack of interpretability in sophisticated AI-based IV-IDSs, it is difficult for humans to trust such systems, let alone know what actions to take when an IDS flags an attack. By using tools found in the area of eXplainable AI (XAI), this thesis aims to explore what kind of explanations could be produced in accord with model predictions, to further increase the trustworthiness of AI-based IV-IDSs. Through a comparative survey, aspects related to trustworthiness and explainability are evaluated on a custom, pseudo-global, visualization-based explanation (”VisExp”), and a rule based explanation. The results show that VisExp increase the trustworthiness,and enhanced the  explainability of the AI-based IV-IDS.

Deep learning methods have the ability to accurately predict and interpret what data represents. However, the decision making of a deep learning model is not comprehensible for humans. This is a problem for sectors like market surveillance which needs clarity in the decision making of the used algorithms. This thesis aimed to investigate how a deep learning model can be constructed to make the decision making of the model humanly comprehensible, and to investigate the potential impact on classification performance. A literature study was performed and publicly available explanation methods were collected. The explanation methods LIME, SHAP, model distillation and SHAP TreeExplainer were implemented and evaluated on a ResNet trained on three different time-series datasets. A decision tree was used as the student model for model distillation, where it was trained with both soft and hard labels. A survey was conducted to evaluate if the explanation method could increase comprehensibility. The results were that all methods could improve comprehensibility for people with experience in machine learning. However, none of the methods could provide full comprehensibility and clarity of the decision making. The model distillation reduced the performance compared to the ResNet model and did not improve the performance of the student model. / Djupinlärningsmetoder har egenskapen att förutspå och tolka betydelsen av data. Däremot så är djupinlärningsmetoders beslut inte förståeliga för människor. Det är ett problem för sektorer som marknadsövervakning som behöver klarhet i beslutsprocessen för använda algoritmer. Målet för den här uppsatsen är att undersöka hur en djupinlärningsmodell kan bli konstruerad för att göra den begriplig för en människa, och att undersöka eventuella påverkan av klassificeringsprestandan. En litteraturstudie genomfördes och publikt tillgängliga förklaringsmetoder samlades. Förklaringsmetoderna LIME, SHAP, modelldestillering och SHAP TreeExplainer blev implementerade och utvärderade med en ResNet modell tränad med tre olika dataset. Ett beslutsträd användes som studentmodell för modelldestillering och den blev tränad på båda mjuka och hårda etiketter. En undersökning genomfördes för att utvärdera om förklaringsmodellerna kan förbättra förståelsen av modellens beslut. Resultatet var att alla metoder kan förbättra förståelsen för personer med förkunskaper inom maskininlärning. Däremot så kunde ingen av metoderna ge full förståelse och insyn på hur beslutsprocessen fungerade. Modelldestilleringen minskade prestandan jämfört med ResNet modellen och förbättrade inte prestandan för studentmodellen.

The thesis investigates how one should determine the appropriate transparency of an information processing system from a receiver perspective. Research in the past has suggested that the model should be maximally transparent for what is labeled as ”high stake decisions”. Instead of motivating the choice of a model’s transparency on the non-rigorous criterion that the model contributes to a high stake decision, this thesis explores an alternative method. The suggested method involves that one should let the transparency depend on how well an explanation of the model’s output satisfies the purpose of an explanation. As a result, we do not have to bother if it is a high stake decision, we should instead make sure the model is sufficiently transparent to provide an explanation that satisfies the expressed purpose of an explanation.

In the past few years, Artificial Intelligence (AI) has evolved into a powerful tool applied in multi-disciplinary fields to resolve sophisticated problems. As AI becomes more powerful and ubiquitous, oftentimes the AI methods also become opaque, which might lead to trust issues for the users of the AI systems as well as fail to meet the legal requirements of AI transparency. In this report, the possibility of making a credit-card fraud detection support system explainable to users is investigated through a quantitative survey. A publicly available credit card dataset was used. Deep Learning and Random Forest were the two Machine Learning (ML) methodsimplemented and applied on the credit card fraud dataset, and the performance of their results was evaluated in terms of their accuracy, recall, sufficiency, and F1 score. After that, two explainable AI (XAI) methods - SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) were implemented and applied to the results obtained from these two ML methods. Finally, the XAI results were evaluated through a quantitative survey. The results from the survey revealed that the XAI explanations can slightly increase the users' impression of the system's ability to reason and LIME had a slight advantage over SHAP in terms of explainability. Further investigation of visualizing data pre-processing and the training process is suggested to offer deep explanations for users.

Online supervised learning from fast-evolving imbalanced data streams has applications in many areas. That is, the development of techniques that are able to handle highly skewed class distributions (or 'class imbalance') is an important area of research in domains such as manufacturing, the environment, and health. Solutions should be able to analyze large repositories in near real-time and provide accurate models to describe rare classes that may appear infrequently or in bursts while continuously accommodating new instances. Although numerous online learning methods have been proposed to handle binary class imbalance, solutions suitable for multi-class streams with varying degrees of imbalance in evolving streams have received limited attention. To address this knowledge gap, the first contribution of this thesis introduces the Online Learning from Imbalanced Multi-Class Streams through Dynamic Sampling (DynaQ) algorithm for learning in such multi-class imbalanced settings. Our approach utilizes a queue-based learning method that dynamically creates an instance queue for each class. The number of instances is balanced by maintaining a queue threshold and removing older samples during training. In addition, new and rare classes are dynamically added to the training process as they appear. Our experimental results confirm a noticeable improvement in minority-class detection and classification performance. A comparative evaluation shows that the DynaQ algorithm outperforms the state-of-the-art approaches. Our second contribution in this thesis focuses on fairness-aware learning from imbalanced streams. Our work is motivated by the observation that the decisions made by online learning algorithms may negatively impact individuals or communities. Indeed, the development of approaches to handle these concerns is an active area of research in the machine learning community. However, most existing methods process the data in offline settings and are not directly suitable for online learning from evolving data streams. Further, these techniques fail to take the effects of class imbalance, on fairness-aware supervised learning into account. In addition, recent fairness-aware online learning supervised learning approaches focus on one sensitive attribute only, which may lead to subgroup discrimination. In a fair classification, the equality of fairness metrics across multiple overlapping groups must be considered simultaneously. In our second contribution, we thus address the combined problem of fairness-aware online learning from imbalanced evolving streams, while considering multiple sensitive attributes. To this end, we introduce the Multi-Sensitive Queue-based Online Fair Learning (MQ-OFL) algorithm, an online fairness-aware approach, which maintains valid and fair models over evolving streams. MQ-OFL changes the training distribution in an online fashion based on both stream imbalance and discriminatory behavior of the model evaluated over the historical stream. We compare our MQ-OFL method with state-of-art studies on real-world datasets and present comparative insights on the performance. Our final contribution focuses on explainability and interpretability in fairness-aware online learning. This research is guided by the concerns raised due to the black-box nature of models, concealing internal logic from users. This lack of transparency poses practical and ethical challenges, particularly when these algorithms make decisions in finance, healthcare, and marketing domains. These systems may introduce biases and prejudices during the learning phase by utilizing complex machine learning algorithms and sensitive data. Consequently, decision models trained on such data may make unfair decisions and it is important to realize such issues before deploying the models. To address this issue, we introduce techniques for interpreting the outcomes of fairness-aware online learning. Through a case study predicting income based on features such as ethnicity, biological sex, age, and education level, we demonstrate how our fairness-aware learning process (MQ-OFL) maintains a balance between accuracy and discrimination trade-off using global and local surrogate models.

<p>The International Energy Agency (IEA) estimates that residential and commercial buildings consume 40% of global energy and emit 24% of CO2. A building's design parameters and location significantly impact its energy usage. Adjusting the building parameters and features in an optimum way helps to reduce energy usage and to build energy-efficient buildings. Hence, analyzing the impact of influencing factors is critical to reduce building energy usage.</p> <p>Towards this, artificial intelligence applications, such as Explainable Artificial Intelligence (XAI) and machine learning (ML) identified the key building features to reduce building energy. This is done by analyzing the efficiencies of various building features that impact building energy consumption. For this, the relative importance of input features impacting commercial building energy usage is investigated. Also analyzed is the parametric analysis of the impact of input variables on residential building energy usage. Furthermore, the dependencies and relationships between the design variables of residential buildings were examined. Finally, the study analyzed the impact of location features on cooling energy usage in commercial buildings.</p> <p>For the purpose of energy consumption data analysis, three datasets, named the Commercial Building Energy Consumption Survey (CBECS) datasets gathered in 2012 and 2018, University of California Irvine (UCI) energy efficiency dataset, and Commercial Load Data (CLD) were utilized. For this, Python and WEKA were used. Random Forest, Linear Regression, Bayesian Networks, and Logistic Regression predicted energy consumption using datasets. Moreover, statistical tests, such as the Wilcoxon-rank sum test were analyzed for the significant differences between specific datasets. Shapash, a Python library, created the feature important graphs.</p> <p>The results indicated that cooling degree days are the most important feature in predicting cooling load with contribution values 34.29% (2018) and 19.68% (2012). Also, analyzing the impact of building parameters on energy usage indicated that 50% of overall height reduction achieves a reduction of heating load by 64.56% and cooling load by 57.47%. Also, the Wilcoxon-rank sum test indicated that the location of the building also impacts energy consumption with a 0.05 error margin. The proposed analysis is beneficial for real-world applications and energy-efficient building construction.</p>

Machine learning has revolutionized recommendation systems by employing ranking models for personalized item suggestions. However, the complexity of learning-to-rank (LTR) models poses challenges in understanding the underlying reasons contributing to the ranking outcomes. This lack of transparency raises concerns about potential errors, biases, and ethical implications. To address these issues, interpretable LTR models have emerged as a solution. Currently, the state-of-the-art for interpretable LTR models is led by generalized additive models (GAMs). However, ranking GAMs face limitations in terms of computational intensity and handling high-dimensional data. To overcome these drawbacks, post-hoc methods, including local interpretable modelagnostic explanations (LIME), have been proposed as potential alternatives. Nevertheless, a quantitative evaluation comparing post-hoc methods efficacy to state-of-the-art ranking GAMs remains largely unexplored. This study aims to investigate the capabilities and limitations of LIME in an attempt to approximate a complex ranking model using a surrogate model. The proposed methodology for this study is an experimental approach. The neural ranking GAM, trained on two benchmark information retrieval datasets, serves as the ground truth for evaluating LIME’s performance. The study adapts LIME in the context of ranking by translating the problem into a classification task and asses three different sampling strategies against the prevalence of imbalanced data and their influence on the correctness of LIME’s explanations. The findings of this study contribute to understanding the limitations of LIME in the context of ranking. It analyzes the low similarity between the explanations of LIME and those generated by the ranking model, highlighting the need to develop more robust sampling strategies specific to ranking. Additionally, the study emphasizes the importance of developing appropriate evaluation metrics for assessing the quality of explanations in ranking tasks.

Machine Learning (ML) and Artificial Intelligence (AI) impact many aspects of human life, from recommending a significant other to assist the search for extraterrestrial life. The area develops rapidly and exiting unexplored design spaces are constantly laid bare. The focus in this work is one of these areas; ML systems where decisions concerning ML model training, usage and selection of target domain lay in the hands of domain experts.  This work is then on ML systems that function as a tool that augments and/or enhance human capabilities. The approach presented is denoted Human In Command ML (HIC-ML) systems. To enquire into this research domain design experiments of varying fidelity were used. Two of these experiments focus on augmenting human capabilities and targets the domains commuting and sorting batteries. One experiment focuses on enhancing human capabilities by identifying similar hand-painted plates. The experiments are used as illustrative examples to explore settings where domain experts potentially can: independently train an ML model and in an iterative fashion, interact with it and interpret and understand its decisions.  HIC-ML should be seen as a governance principle that focuses on adding value and meaning to users. In this work, concrete application areas are presented and discussed. To open up for designing ML-based products for the area an abstract model for HIC-ML is constructed and design guidelines are proposed. In addition, terminology and abstractions useful when designing for explicability are presented by imposing structure and rigidity derived from scientific explanations. Together, this opens up for a contextual shift in ML and makes new application areas probable, areas that naturally couples the usage of AI technology to human virtues and potentially, as a consequence, can result in a democratisation of the usage and knowledge concerning this powerful technology.