The mining of justifications to be recommended to visitors of deliberation for a used in decision making by constituents raises specific challenges. Graph-based representations can improve our understanding of the problem and enable reasoning with the available data. The addressed technical problem consists in recommending sets of texts containing comprehensive arguments supporting or opposing poll alternatives, as mined from submissions of opinions in electronic deliberative polls. A graphical framework is proposed to enable the development of techniques for identification of relevant/encompassing arguments in debates following the Alternative-Based Information System (ABIS) model, a competitor of the IBIS model. Bipolar argumentation frameworks are extended with votes, enhance relations and argument coalitions, proposing the BAPDF family of frameworks.

Explainable AI – or XAI – is a relatively new research area that hopes to'open the black box' on deep learning neural networks, complex algorithms and probabilistic graphical models. Artificial intelligence systems that can explain their decision making process in human terms are now the subject of intense research by software and cloud vendor Oracle, the company's senior vice-president of data-driven applications revealed to Computerworld yesterday. "One thing we don't make a big call out to is that we have a dedicated research team at Oracle called Oracle labs, mostly PhD computer scientists. And we have a lot of research going on that we don't tend to advertise very much in those research groups looking into that specific research area," said Clive Swan on the fringes of Oracle's Modern Business Experience event in Sydney. "It remains a big area of academic research. That problem is…very difficult academically to solve in some cases, and frankly varies from algorithm to algorithm."

At a demonstration of Amazon Web Services' new artificial intelligence image recognition tool last week, the deep learning analysis calculated with near certainty that a photo of speaker Glenn Gore depicted a potted plant. "It is very clever, it can do some amazing things but it needs a lot of hand holding still. AI is almost like a toddler. They can do some pretty cool things, sometimes they can cause a fair bit of trouble," said AWS' chief architect in his day two keynote at the company's summit in Sydney. Where the toddler analogy falls short, however, is that a parent can make a reasonable guess as to, say, what led to their child drawing all over the walls, and ask them why.

An inconsistent knowledge base can be abstracted as a set of arguments and a defeat relation among them. There can be more than one consistent way to evaluate such an argumentation graph. Collective argument evaluation is the problem of aggregating the opinions of multiple agents on how a given set of arguments should be evaluated. It is crucial not only to ensure that the outcome is logically consistent, but also satisfies measures of social optimality and immunity to strategic manipulation. This is because agents have their individual preferences about what the outcome ought to be. In the current paper, we analyze three previously introduced argument-based aggregation operators with respect to Pareto optimality and strategy proofness under different general classes of agent preferences. We highlight fundamental trade-offs between strategic manipulability and social optimality on one hand, and classical logical criteria on the other. Our results motivate further investigation into the relationship between social choice and argumentation theory. The results are also relevant for choosing an appropriate aggregation operator given the criteria that are considered more important, as well as the nature of agents' preferences.

Artificial Intelligence offers a lot of advantages for organisations by creating better and more efficient organisations, improving customer services with conversational AI and reducing a wide variety of risks in different industries. Although we are only at the beginning of the AI revolution that is upon us, we can already see that artificial intelligence will have a profound effect on our lives. As a result, AI governance and Explainable AI are becoming increasingly important, if we want to reap the benefits of artificial intelligence. Data governance and ethics have always been important and a few years ago, I developed ethical guidelines for organisations to follow, if they want to get started with big data. Such ethical guidelines are becoming more important, especially now since algorithms are taking over more and more decisions.

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.

With the news that Zelda: Breath of the Wild will feature DLC, it has been met with a very mixed response by fans. In a recent interview, Nintendo's Bill Trinen does his best to explain the reasoning behind this decision. The main takeaway from Trinen's explanation (starting at 41:42 in the below video) is that Breath of the Wild is obviously a very large game in terms of its content and production. The DLC in that sense is a byproduct of that, as the complexity of developing an open world game means there is more left to do. So this DLC release, in part, is Nintendo's attempt at including absolutely everything it can from Breath of the Wild's production. In all honesty, this is entirely understandable.

On the Web, there is always a need to aggregate opinions from the crowd (as in posts, social networks, forums, etc.). Different mechanisms have been implemented to capture these opinions such as "Like" in Facebook, "Favorite" in Twitter, thumbs-up/down, flagging, and so on. However, in more contested domains (e.g. Wikipedia, political discussion, and climate change discussion) these mechanisms are not sufficient since they only deal with each issue independently without considering the relationships between different claims. We can view a set of conflicting arguments as a graph in which the nodes represent arguments and the arcs between these nodes represent the defeat relation. A group of people can then collectively evaluate such graphs. To do this, the group must use a rule to aggregate their individual opinions about the entire argument graph. Here, we present the first experimental evaluation of different principles commonly employed by aggregation rules presented in the literature. We use randomized controlled experiments to investigate which principles people consider better at aggregating opinions under different conditions. Our analysis reveals a number of factors, not captured by traditional formal models, that play an important role in determining the efficacy of aggregation. These results help bring formal models of argumentation closer to real-world application.

We present an approach to reasoning with strict and defeasible rules over literals. A controlled natural language is employed as human/machine interface to facilitate the specification of knowledge and verbalization of results. Reasoning on the rules is done by a direct semantics that addresses several issues for current approaches to argumentation-based defeasible reasoning. Techniques from formal argumentation theory are employed to justify conclusions of the approach; therefore, we not only address automated reasoning but also human acceptance of provided conclusions.

As autonomous intelligent systems become more widespread, society is beginning to ask: "What are the machines up to?". Various forms of artificial intelligence control our latest cars, load balance components of our power grids, dictate much of the movement in our stock markets and help doctors diagnose and treat our ailments. As they become increasingly able to learn and model more complex phenomena, so the ability of human users to understand the reasoning behind their decisions often decreases. It becomes very difficult to ensure that the robot will perform properly and that it is possible to correct errors. In this paper, we outline a variety of techniques for generating the underlying knowledge required for explainable artificial intelligence, ranging from early work in expert systems through to systems based on Behavioural Cloning. These are techniques that may be used to build intelligent robots that explain their decisions and justify their actions. We will then illustrate how decision trees are particularly well suited to generating these kinds of explanations. We will also discuss how additional explanations can be obtained, beyond simply the structure of the tree, based on knowledge of how the training data was generated. Finally, we will illustrate these capabilities in the context of a robot learning to drive over rough terrain in both simulation and in reality.