Class expression learning is a branch of explainable supervised machine learning of increasing importance. Most existing approaches for class expression learning in description logics are search algorithms or hard-rule-based. In particular, approaches based on refinement operators suffer from scalability issues as they rely on heuristic functions to explore a large search space for each learning problem. We propose a new family of approaches, which we dub synthesis approaches. Instances of this family compute class expressions directly from the examples provided. Consequently, they are not subject to the runtime limitations of search-based approaches nor the lack of flexibility of hard-rule-based approaches. We study three instances of this novel family of approaches that use lightweight neural network architectures to synthesize class expressions from sets of positive examples. The results of their evaluation on four benchmark datasets suggest that they can effectively synthesize high-quality class expressions with respect to the input examples in under a second on average. Moreover, a comparison with the state-of-the-art approaches CELOE and ELTL suggests that we achieve significantly better F-measures on large ontologies. For reproducibility purposes, we provide our implementation as well as pre-trained models in the public GitHub repository at https://github.com/ConceptLengthLearner/NCES

AI-enhanced cybersecurity is a must in 2021 and beyond. Clearly, the industry agrees -- you'll find an endless list of AI security platforms in the marketplace. What do vendors really mean when they use the term "artificial intelligence?" AI can be a fluid term, and sometimes mean different things to different people, and although marketing teams at cyber companies are using this ambiguity to their advantage, too often when it comes to the actual implementation and use of these platforms, the technology and promise falls short of AI in it's true scientific sense. Some artificial intelligence is and will be groundbreaking for the cybersecurity industry.

This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjunctive normal form (CNF, AND-of-ORs) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy for rule simplicity. We also consider the fairness setting and extend the formulation to include explicit constraints on two different measures of classification parity: equality of opportunity and equalized odds. Column generation (CG) is used to efficiently search over an exponential number of candidate clauses (conjunctions or disjunctions) without the need for heuristic rule mining. This approach also bounds the gap between the selected rule set and the best possible rule set on the training data. To handle large datasets, we propose an approximate CG algorithm using randomization. Compared to three recently proposed alternatives, the CG algorithm dominates the accuracy-simplicity trade-off in 8 out of 16 datasets. When maximized for accuracy, CG is competitive with rule learners designed for this purpose, sometimes finding significantly simpler solutions that are no less accurate. Compared to other fair and interpretable classifiers, our method is able to find rule sets that meet stricter notions of fairness with a modest trade-off in accuracy.

Possibilistic logic is the most popular approach to represent and reason with uncertain and partially inconsistent knowledge. Regarding normal forms, the encoding of real-world problems does usually not result in a clausal formula and although a possibility nonclausal formula is theoretically equivalent to some possibilistic clausal formula [26, 22], approaches needing clausal form transformations are practically infeasible or have experimentally shown to be highly inefficient as discussed below. Two kinds of clausal form transformation are known: (1) one is based on the repetitive application of the distributive laws to the input non-clausal formula until a logically equivalent clausal formula is obtained; and (2) the other transformation, Tsetin-transformation [59], is based on recursively substituting sub-formulas in the input non-clausal formula by fresh literals until obtaining an equi-satisfiable, but not equivalent, clausal formula.

International economics has a long history of improving our understanding of factors causing trade, and the consequences of free flow of goods and services across countries. The recent shocks to the free trade regime, especially trade disputes among major economies, as well as black swan events, such as trade wars and pandemics, raise the need for improved predictions to inform policy decisions. AI methods are allowing economists to solve such prediction problems in new ways. In this manuscript, we present novel methods that predict and associate food and agricultural commodities traded internationally. Association Rules (AR) analysis has been deployed successfully for economic scenarios at the consumer or store level, such as for market basket analysis. In our work however, we present analysis of imports and exports associations and their effects on commodity trade flows. Moreover, Ensemble Machine Learning methods are developed to provide improved agricultural trade predictions, outlier events' implications, and quantitative pointers to policy makers.

Artificial Intelligence (AI) algorithms are increasingly providing decision making and operational support across multiple domains. AI includes a wide library of algorithms for different problems. One important notion for the adoption of AI algorithms into operational decision process is the concept of assurance. The literature on assurance, unfortunately, conceals its outcomes within a tangled landscape of conflicting approaches, driven by contradicting motivations, assumptions, and intuitions. Accordingly, albeit a rising and novel area, this manuscript provides a systematic review of research works that are relevant to AI assurance, between years 1985 - 2021, and aims to provide a structured alternative to the landscape. A new AI assurance definition is adopted and presented and assurance methods are contrasted and tabulated. Additionally, a ten-metric scoring system is developed and introduced to evaluate and compare existing methods. Lastly, in this manuscript, we provide foundational insights, discussions, future directions, a roadmap, and applicable recommendations for the development and deployment of AI assurance.

Every step we take in the digital world leaves behind a record of our behavior; a digital footprint. Research has suggested that algorithms can translate these digital footprints into accurate estimates of psychological characteristics, including personality traits, mental health or intelligence. The mechanisms by which AI generates these insights, however, often remain opaque. In this paper, we show how Explainable AI (XAI) can help domain experts and data subjects validate, question, and improve models that classify psychological traits from digital footprints. We elaborate on two popular XAI methods (rule extraction and counterfactual explanations) in the context of Big Five personality predictions (traits and facets) from financial transactions data (N = 6,408). First, we demonstrate how global rule extraction sheds light on the spending patterns identified by the model as most predictive for personality, and discuss how these rules can be used to explain, validate, and improve the model. Second, we implement local rule extraction to show that individuals are assigned to personality classes because of their unique financial behavior, and that there exists a positive link between the model's prediction confidence and the number of features that contributed to the prediction. Our experiments highlight the importance of both global and local XAI methods. By better understanding how predictive models work in general as well as how they derive an outcome for a particular person, XAI promotes accountability in a world in which AI impacts the lives of billions of people around the world.

We present a parallel version of Sch\"onhage's Storage Modification Machine, the Multiway Storage Modification Machine (MWSMM). Like the alternative Association Storage Modification Machine of Tromp and van Emde Boas, MWSMMs recognize in polynomial time what Turing Machines recognize in polynomial space. Falling thus into the Second Machine Class, the MWSMM is a parallel machine model conforming to the Parallel Computation Thesis. We illustrate MWSMMs by a simple implementation of Wolfram's String Substitution System.

For most organizations, the bifurcation of Artificial Intelligence has been as stark as it's been simplistic. AI was either machine learning or rules-based approaches (the former of which outnumbered the latter), supervised or unsupervised learning, computer vision or natural language technologies. Due to a number of developments in the past year around ModelOps, composite AI, and neuro-symbolic AI, there's currently a growing awareness throughout the enterprise that AI--and its ROI--not only involves each of the foresaid dimensions, but does so optimally when they operate in conjunction with each other to pare the costs, difficulty, and time they otherwise require. CTO Marco Varone, "There are situations where you can get better results combining the different approaches; there are situations where you can use both and it's not too different, and there are situations where it's better with one approach." By incorporating the full AI spectrum into their toolkits, organizations can not only deploy the most appropriate method for their cognitive computing tasks, but also exploit surrounding areas of opportunity like intellectual property for machine learning models, cloud or Internet of Things use cases, and explainable AI. "The future is what we call a hybrid or composite approach where you use all the techniques that are available and you put them together in a way that the end user or data scientist trying to solve a specific problem can take different techniques and decide to use the ones giving the best results," Varone predicted.

Detection of malicious activities in corporate environments is a very complex task and much effort has been invested into research of its automation. However, vast majority of existing methods operate only in a narrow scope which limits them to capture only fragments of the evidence of malware's presence. Consequently, such approach is not aligned with the way how the cyber threats are studied and described by domain experts. In this work, we discuss these limitations and design a detection framework which combines observed events from different sources of data. Thanks to this, it provides full insight into the attack life cycle and enables detection of threats that require this coupling of observations from different telemetries to identify the full scope of the incident. We demonstrate applicability of the framework on a case study of a real malware infection observed in a corporate network.