Bipolar Argumentation Frameworks (BAFs) admit several interpretations of the support relation and diverging definitions of semantics. Recently, several classes of BAFs have been captured as instances of bipolar Assumption-Based Argumentation, a class of Assumption-Based Argumentation (ABA). In this paper, we establish the complexity of bipolar ABA, and consequently of several classes of BAFs. In addition to the standard five complexity problems, we analyse the rarely-addressed extension enumeration problem too. We also advance backtracking-driven algorithms for enumerating extensions of bipolar ABA frameworks, and consequently of BAFs under several interpretations. We prove soundness and completeness of our algorithms, describe their implementation and provide a scalability evaluation. We thus contribute to the study of the as yet uninvestigated complexity problems of (variously interpreted) BAFs as well as of bipolar ABA, and provide the lacking implementations thereof.

In this paper, we introduce a formalism for single-agent decision making that is based on Dynamic Argumentation Frameworks. The formalism can be used to justify a choice, which is based on the current situation the agent is involved. Taking advantage of the inference mechanism of the argumentation formalism, it is possible to consider preference relations and conflicts among the available alternatives for that reasoning. With this formalization, given a particular set of evidence, the justified conclusions supported by warranted arguments will be used by the agent's decision rules to determine which alternatives will be selected. We also present an algorithm that implements a choice function based on our formalization. Finally, we complete our presentation by introducing formal results that relate the proposed framework with approaches of classical decision theory.

Augmented analytics, continuous intelligence and explainable artificial intelligence (AI) are among the top trends in data and analytics technology that have significant disruptive potential over the next three to five years, according to Gartner, Inc. Speaking at the Gartner Data & Analytics Summit in Sydney today, Rita Sallam, research vice president at Gartner, said data and analytics leaders must examine the potential business impact of these trends and adjust business models and operations accordingly, or risk losing competitive advantage to those who do. "The story of data and analytics keeps evolving, from supporting internal decision making to continuous intelligence, information products and appointing chief data officers," she said. "It's critical to gain a deeper understanding of the technology trends fueling that evolving story and prioritize them based on business value." According to Donald Feinberg, vice president and distinguished analyst at Gartner, the very challenge created by digital disruption -- too much data -- has also created an unprecedented opportunity. The vast amount of data, together with increasingly powerful processing capabilities enabled by the cloud, means it is now possible to train and execute algorithms at the large scale necessary to finally realize the full potential of AI. "The size, complexity, distributed nature of data, speed of action and the continuous intelligence required by digital business means that rigid and centralized architectures and tools break down," Mr. Feinberg said.

Los Angeles Rams running back Todd Gurley reportedly has been diagnosed with arthritis in his left knee, according to Jeff Howe of theathletic.com. Gurley was used very sparingly in the 2018 playoffs, especially after the divisional round game against Dallas. The diagnosis could explain the reasoning for his lack of carries during the Rams' playoff run, which ended against the Patriots in the Super Bowl. His knee issues started earlier in the season, when he was forced to miss the final two games against Arizona and San Francisco. Back in December, the Rams said it was just soreness and inflammation.

Training an artificial intelligence (AI) algorithm requires data--lots of data. But staying GDPR-compliant while acquiring that data can be almost impossible. Here's the problem: To make a decision about someone--e.g., that they like the color blue and should be targeted with blue advertisements--an AI algorithm combines their personal data with other data inside its big black box, and spits out the answer. To get the data the AI needs, GDPR requires companies to get consent to use that personal data, tell that person exactly what it's being used for, and guarantee it won't be used for anything else. But companies have no idea what's happening inside that black box, so true consent becomes a myth. Article 22 of GDPR complicates the issue by giving consumers the right to not have an automated process make a decision about them that has legal affects or otherwise "significantly effects them."

In abstract argumentation, multiple argumentation semantics have been proposed that allow to select sets of jointly acceptable arguments from a given argumentation framework, i.e. based only on the attack relation between arguments. The existence of multiple argumentation semantics raises the question which of these semantics predicts best how humans evaluate arguments. Previous empirical cognitive studies that have tested how humans evaluate sets of arguments depending on the attack relation between them have been limited to a small set of very simple argumentation frameworks, so that some semantics studied in the literature could not be meaningfully distinguished by these studies. In this paper we report on an empirical cognitive study that overcomes these limitations by taking into consideration twelve argumentation frameworks of three to eight arguments each. These argumentation frameworks were mostly more complex than the argumentation frameworks considered in previous studies. All twelve argumentation framework were systematically instantiated with natural language arguments based on a certain fictional scenario, and participants were shown both the natural language arguments and a graphical depiction of the attack relation between them. Our data shows that grounded and CF2 semantics were the best predictors of human argument evaluation. A detailed analysis revealed that part of the participants chose a cognitively simpler strategy that is predicted very well by grounded semantics, while another part of the participants chose a cognitively more demanding strategy that is mostly predicted well by CF2 semantics.

One of the challenges of using artificial intelligence solutions in the enterprise is that the technology operates in what is commonly referred to as a black box. Often, artificial intelligence (AI) applications employ neural networks that produce results using algorithms with a complexity level that only computers can make sense of. In other instances, AI vendors will not reveal how their AI works. In either case, when conventional AI produces a decision, human end users don't know how it arrived at its conclusions. This black box can pose a significant obstacle.

Automatically reasoning with conflicting generic clinical guidelines is a burning issue in patient-centric medical reasoning where patient-specific conditions and goals need to be taken into account. It is even more challenging in the presence of preferences such as patient's wishes and clinician's priorities over goals. We advance a structured argumentation formalism for reasoning with conflicting clinical guidelines, patient-specific information and preferences. Our formalism integrates assumption-based reasoning and goal-driven selection among reasoning outcomes. Specifically, we assume applicability of guideline recommendations concerning the generic goal of patient well-being, resolve conflicts among recommendations using patient's conditions and preferences, and then consider prioritised patient-centered goals to yield non-conflicting, goal-maximising and preference-respecting recommendations. We rely on the state-of-the-art Transition-based Medical Recommendation model for representing guideline recommendations and augment it with context given by the patient's conditions, goals, as well as preferences over recommendations and goals. We establish desirable properties of our approach in terms of sensitivity to recommendation conflicts and patient context.

Most work on interpretability in machine learning has focused on designing either inherently interpretable models, that typically trade-off interpretability for accuracy, or post-hoc explanation systems, that lack guarantees about their explanation quality. We propose an alternative to these approaches by directly regularizing a black-box model for interpretability at training time. Our approach explicitly connects three key aspects of interpretable machine learning: the model's innate explainability, the explanation system used at test time, and the metrics that measure explanation quality. Our regularization results in substantial (up to orders of magnitude) improvement in terms of explanation fidelity and stability metrics across a range of datasets, models, and black-box explanation systems. Remarkably, our regularizers also slightly improve predictive accuracy on average across the nine datasets we consider. Further, we show that the benefits of our novel regularizers on explanation quality provably generalize to unseen test points.