scispace - formally typeset
Search or ask a question

Showing papers in "Artificial Intelligence in 2019"


Journal ArticleDOI
TL;DR: This paper argues that the field of explainable artificial intelligence should build on existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics, and draws out some important findings.

2,585 citations



Journal ArticleDOI
TL;DR: This work introduces the stability of a sample to quantify its contribution and presents a methodology to determine this stability, and develops a clustering ensemble algorithm based on the sample's stability that statistically outperforms twelve state-of-the-art clusteringsemble algorithms on ten real data sets from UCI and six document data sets.

68 citations


Journal ArticleDOI
TL;DR: IRT suits classification tasks perfectly, where instances correspond to items and classifiers correspond to respondents and how the estimated classifier ability can be used to compare classifier performance in a different way through classifier characteristic curves is seen.

59 citations


Journal ArticleDOI
TL;DR: A hybrid model, which is hybridized by empirical mode decomposition, stacked auto-encoders, and extreme learning machines, aiming to forecast wind speed accurately and efficiently is proposed, and the effectiveness of the shared-hidden-layer approach for deep networks is demonstrated.

48 citations


Journal ArticleDOI
TL;DR: This paper offers a new heterogeneous transfer learning framework named Hybrid Heterogeneous Transfer Learning (HHTL), which allows the selection of corresponding instances across domains to be biased to the source or target domain.

43 citations


Journal ArticleDOI
TL;DR: FAMA is a novel approach for learning Strips action models from observations of plan executions that compiles the learning task into a classical planning task and its performance is compared to ARMS, a state-of-the-art benchmark in action model learning.

36 citations


Journal ArticleDOI
TL;DR: It is proved that a simple multi-objective EA called GSEMO-C can generally achieve good approximation guarantees in polynomial expected running time.

36 citations


Journal ArticleDOI
TL;DR: An analysis for the standard NP-Hard Partition problem from combinatorial optimisation is performed and it is proved that while EAs and Random Local Search may get trapped on 4/3 approximations, AISs find arbitrarily good approximate solutions of ratio (\(1+\epsilon) \) within a time that is polynomial in the problem size and exponential only in \(1/\ep silon \).

34 citations


Journal ArticleDOI
TL;DR: This work presents protocols for democratic fair allocation among two or more arbitrarily large groups of agents with monotonic, additive, or binary valuations, and gives an efficient protocol that guarantees envy-freeness up to one good for at least 1/2 of the agents in each group, and proves that the 1/1 fraction is optimal.

33 citations


Journal ArticleDOI
TL;DR: This paper extends the conventional attentional encoder-decoder NMT framework by introducing a backward decoder, in order to explore asynchronous bidirectional decoding for NMT, and achieves significant improvements over the conventional RNNSearch.

Journal ArticleDOI
TL;DR: Three algorithms for datalog with stratified negation are presented: a new counting algorithm that can handle recursive rules, an optimised variant of the DRed algorithm that does not repeat derivations, and a new Forward/Backward/Forward algorithm that extends DRed to better handle facts with multiple derivations.

Journal ArticleDOI
TL;DR: Experiments on real car, taxi and bus traces show that CoTrans, with no need of a pre-labeled ridesharing dataset, can outperform state-of-the-art transfer learning methods with an accuracy comparable to human labeling.

Journal ArticleDOI
TL;DR: In this article, the authors report on the state of the art in algorithm selection, as defined by the Algorithm Selection competitions in 2015 and 2017, and show that although performance in some cases is very good, there is still room for improvement in other cases.

Journal ArticleDOI
TL;DR: The 2016 and 2017 competitive evaluations of QBF solvers (QBFE VAL'16 and QBFEVAL'17), the two most recent events in a series of competitions established with the aim of assessing the advancements in reasoning about QBFs are reported on.

Journal ArticleDOI
TL;DR: This paper shows that for sufficiently expressive description logics, the traditional correspondence between rational closure and ranked interpretations does not hold, and introduces stable rational closure, based on stable rankings, a natural extension of the standard rational closure.

Journal ArticleDOI
TL;DR: In this article, the authors propose a strategy-proof mechanism for peer selection, i.e., agents cannot benefit by reporting insincere valuations, and demonstrate the effectiveness of their mechanism by a comprehensive simulation-based comparison with a suite of mechanisms found in the literature.

Journal ArticleDOI
Ke Wang1, Xiaojun Wan1
TL;DR: Experimental results on a variety of datasets demonstrate that the SentiGAN model consistently outperforms several state-of-the-art text generation models in the sentiment accuracy and quality of generated texts.

Journal ArticleDOI
TL;DR: This paper proposed a non-binary shift-reduce algorithm for constituent parsing, which can generate nonbinary branchings with just one Reduce transition, instead of requiring prior binarization or a sequence of binary transitions.

Journal ArticleDOI
Igor Douven1
TL;DR: The main methodology to be used is that of agent-based optimization, which is a specific form of evolutionary computing, and this methodology is implemented in a generalization of the Hegselmann–Krause model.

Journal ArticleDOI
TL;DR: Interestingly, the introduction of gen is shown to be also a standalone contribution as a powerful representation paradigm for prAAFs, owing to its high expressiveness, compactness, and the possibility to support user-friendly mechanisms for defining correlations.

Journal ArticleDOI
TL;DR: A novel formalism for representing generalized plans that borrows two mechanisms from structured programming: control flow and procedure calls is introduced that allows to compactly represent generalized plans.

Journal ArticleDOI
TL;DR: This paper aims to understand human activities being performed in real-world environments from long-term observation from an autonomous mobile robot, and generative probabilistic technique is used to recover latent, semantically-meaningful concepts in the encoded observations in an unsupervised manner.

Journal ArticleDOI
TL;DR: This paper presents a novel formulation of WMI, which allows to exploit the power of SMT-based predicate abstraction techniques in designing efficient inference procedures and combines a strong reduction in the number of models to be integrated over with their efficient enumeration.

Journal ArticleDOI
TL;DR: This paper formally defines what “simple” means, and proposes a variant of alternating-time temporal logic that takes only natural strategies into account, and shows that, by adopting the view of bounded rationality, the complexity of rational verification for multi-agent systems is significantly decreased.

Journal ArticleDOI
TL;DR: This paper defines an AP between formal concepts and to give algorithms to compute them, but also to point to special subcontexts, called analogical complexes, which are themselves organized as a lattice and show that they are closely related to APs between concepts, while not needing the complete construction of the lattice.

Journal ArticleDOI
TL;DR: This paper proposes translations of AT L ir formulae that provide lower and upper bounds for their truth values, and are cheaper to verify than the original specifications, and shows that these approximations can be combined with under- and overapproximations of models in the vein of may/must abstractions, providing very promising experimental results.

Journal ArticleDOI
TL;DR: A notion of empathy in social networks is introduced, in which individuals derive utility based on both their own intrinsic preferences, and empathetic preferences determined by the satisfaction of their neighbors in the network.

Journal ArticleDOI
TL;DR: A secure implementation of RODA (Region Optimal DCOP Algorithm), called P-RODA, is devised, which preserves constraint privacy and partial decision privacy and gives an upper bound that depends on the group and domain sizes and on the graph topology, but not on the number of agents.

Journal ArticleDOI
TL;DR: It is proved that there exists a unique centrality index satisfying a number of desirable properties, which is equivalent to the Myerson value of a certain graph-restricted game and can be computed in chordal graphs in polynomial time.