Showing papers in "Artificial Intelligence in 2020"

TL;DR: It is argued that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground and developing novel techniques for such theory of mind reasoning will not only be crucial for success in Hanabi, but also in broader collaborative efforts, especially those with human partners.

TL;DR: How early viral detection will reduce in time as computing technology is enhanced and as more data communication and libraries are ensured between varying data information systems is explored.

TL;DR: This work reviews recent state-of-the-art deep learning algorithms and architectures proposed as CAD systems for lung cancer detection and presents the main characteristics of the different techniques, and their performance is analyzed.

TL;DR: A comprehensive review of the variety of techniques for explanation that have been developed in AI and Law and highlights gaps that must be addressed by future systems to ensure that accurate, trustworthy, unbiased decision support can be provided to legal professionals.

TL;DR: A multi-disciplinary perspective from systems engineering, ethics, and law is articulate a common language in which to reason about the multi-faceted problem of assuring the safety of autonomous systems to expose key sources of uncertainty and risk with autonomous systems.

TL;DR: The results show that the diversity of aspects captured by the different interestingness elements is crucial to help humans correctly understand an agent's strengths and limitations in performing a task, and determine when it might need adjustments to improve its performance.

TL;DR: It is shown that the ultimate goal of humankind is to achieve IA through the exploitation of AI, and the urgent need for ethical frameworks that define how AI should be used to trigger the next level of IA is articulated.

TL;DR: An end-to-end methodology for estimating weights of individual participant profiles in a kidney exchange, with certain classes of patients being (de)prioritized based on the human-elicited value judgments.

TL;DR: This second edition of the Second International Competition on Computational Models of Argumentation maintains some of the design choices made in the first event, but introduces significant novelties, e.g. the I/O formats, the basic reasoning problems, and the organization into tasks and tracks.

TL;DR: It is argued that Pareto optimality can be seen as a notion of stability, and the concept of Price of Pare to Optimality is introduced, an analogue of the Price of Anarchy, where the maximum is computed over the class of Paredto optimal outcomes.

TL;DR: Experiments show that the proposed algorithms perform better on classical benchmarks, and obtain the best solutions for most massive graphs, compared to state-of-the-art heuristic algorithms and exact algorithm.

TL;DR: A deeper understanding of AI and how it can be used as a catalyst for business model innovation is provided to provide a roadmap to guide the implementation of AI to firm’s operations.

TL;DR: This work introduces a novel beam search algorithm that facilitates synchronous bidirectional decoding and presents the core approach which enables left-to-right and right- to-left decoding to interact with each other, so as to utilize both the history and future predictions simultaneously during inference.

TL;DR: A CNN model with different number of convolution layers is proposed to detect COVID-19 patients from chest X-ray images and a comparative analysis of how change in convolutional layers and increase in dataset affect classifying performances is shown.

TL;DR: A novel model of online human intention recognition that combines gaze and model-based AI planning to build probability distributions over a set of possible intentions is proposed and indicates that the proposed model could be used to design novel human-agent interactions in cases when the authors are unsure whether a person is honest, deceitful, or semi-rational.

TL;DR: In this article, a method to generate a carrot yield map applying a random forest (RF) regression algorithm on a database composed of satellite spectral data and carrot ground-truth yield sampling was developed.

TL;DR: The proposed Robust SVM+ method maximizes the lower bound of the perturbations that may influence the judgement based on a rigorous theoretical analysis to tackle imperfect data in LUPI.

TL;DR: Some of the most relevant investigations on the subject of automatic pest detection using proximal digital images and machine learning are described to provide a unified overview of the research carried out so far and some possible targets for future research are proposed.

TL;DR: Off-the-shelf theorem provers and model finders for HOL are assisting the LogiKEy designer of ethical intelligent agents to flexibly experiment with underlying logics and their combinations, with ethico-legal domain theories, and with concrete examples---all at the same time.

TL;DR: A melody structure-based model called PopMNet is presented to generate structured pop music melodies that contain much clearer structures compared to those generated by other models, as confirmed by human behavior experiments.

TL;DR: A novel algorithm for Qualitative Case-Based Reasoning and Learning (QCBRL), which is a case-based reasoning system that uses qualitative spatial representations to retrieve and reuse cases by means of relations between objects in the environment, is introduced.

TL;DR: It is shown that the expected runtime of plain evolutionary algorithms like the (1+1) EA increases steeply with the hurdle width, yielding superpolynomial times to find the optimum, whereas a simple memetic algorithm, (1-1) MA, only needs polynomial expected time.

TL;DR: This survey is the first to bridge the two branches of quality control research by providing technical details on how they work together under frameworks that systematically unify crowdsourcing aspects modelled by both of them to determine the response quality.

TL;DR: Across three online experiments, which definitions people perceive to be the fairest in the context of loan decisions are tested, and whether fairness perceptions change with the addition of sensitive information is tested.

TL;DR: A local search algorithm, called SATLike, is proposed, which exploits the structure of Partial MaxSAT by a novel clause weighting scheme and has better performance than state-of-the-art SAT-based solvers on unweighted industrial benchmarks.

TL;DR: An investigation on the structure of conditional events and on the probability measures which arise naturally in that context is presented, and a construction which defines a (finite) Boolean algebra of conditionals from any (finitely) Booleangebra of events is introduced.

TL;DR: This paper shows that there is a fairness dimension to robot navigation, and collects and translates several formal definitions of distributive justice into the navigation planning domain, and uses a walkthrough example of a rescue robot to bring out design choices and issues that arise during the development of a fair system.

TL;DR: Experiments have proven that Train-O-Matic on its own, and also coupled with word sense distribution learning methods, lead a supervised system to achieve state-of-the-art performance consistently across gold standard datasets and languages.

TL;DR: This paper serves as a proof-of-concept that an automated detection approach can be developed with a limited set of COVID-19 images, and in areas with scarcity of trained radiologists.

TL;DR: In this paper, the authors found that the vast majority of teachers think that virtual reality is interesting, encourages students to be active, is suitable for students with schematic and visual thinking style, provides students with a general idea about the subject, facilitates the implementation of information, makes it easier to learn, and provides a quick review of the course they have studied.