Feature selection and attribute reduction are crucial problems, and widely used techniques in the field of machine learning, data mining and pattern recognition to overcome the well-known phenomenon of the Curse of Dimensionality, by either selecting a subset of features or removing unrelated ones. This paper presents a new feature selection method that efficiently carries out attribute reduction, thereby selecting the most informative features of a dataset. It consists of two components: 1) a measure for feature subset evaluation, and 2) a search strategy. For the evaluation measure, we have employed the fuzzy-rough dependency degree (FRFDD) in the lower approximation-based fuzzy-rough feature selection (L-FRFS) due to its effectiveness in feature selection. As for the search strategy, a new version of a binary shuffled frog leaping algorithm is proposed (B-SFLA). The new feature selection method is obtained by hybridizing the B-SFLA with the FRDD. Non-parametric statistical tests are conducted to compare the proposed approach with several existing methods over twenty two datasets, including nine high dimensional and large ones, from the UCI repository. The experimental results demonstrate that the B-SFLA approach significantly outperforms other metaheuristic methods in terms of the number of selected features and the classification accuracy.

Leadership games provide a powerful paradigm to model many real-world settings. Most literature focuses on games with a single follower who acts optimistically, breaking ties in favour of the leader. Unfortunately, for real-world applications, this is unlikely. In this paper, we look for efficiently solvable games with multiple followers who play either optimistically or pessimistically, i.e., breaking ties in favour or against the leader. We study the computational complexity of finding or approximating an optimistic or pessimistic leader-follower equilibrium in specific classes of succinct games-- polymatrix like--which are equivalent to 2-player Bayesian games with uncertainty over the follower, with interdependent or independent types. Furthermore, we provide an exact algorithm to find a pessimistic equilibrium for those game classes. Finally, we show that in general polymatrix games the computation is harder even when players are forced to play pure strategies. Introduction Leadership games have recently received a lot of attention in the Artificial Intelligence literature, also thanks to their use in many real-world applications, e.g., security and protection (Basilico, De Nittis, and Gatti 2017; Kar et al. 2017a; Kar et al. 2017b). In principle, the paradigm is simple--one or more leaders commit to a potentially mixed strategy, the followers observe the commitments, and then they play their best-responses--, but it can be declined in many different ways. The crucial issue is the computational study of the problem of finding the best leaders' strategy. In this paper, we provide new computational complexity results and algorithms for games with one leader and two or more followers.

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to vocoders and hence they are often called neural vocoders. The neural vocoder uses acoustic features as local condition parameters, and these parameters need to be accurately predicted by another acoustic model. However, it is not yet clear how to train this acoustic model, which is problematic because the final quality of synthetic speech is significantly affected by the performance of the acoustic model. Significant degradation happens, especially when predicted acoustic features have mismatched characteristics compared to natural ones. In order to reduce the mismatched characteristics between natural and generated acoustic features, we propose frameworks that incorporate either a conditional generative adversarial network (GAN) or its variant, Wasserstein GAN with gradient penalty (WGAN-GP), into multi-speaker speech synthesis that uses the WaveNet vocoder. We also extend the GAN frameworks and use the discretized mixture logistic loss of a well-trained WaveNet in addition to mean squared error and adversarial losses as parts of objective functions. Experimental results show that acoustic models trained using the WGAN-GP framework using back-propagated discretized-mixture-of-logistics (DML) loss achieves the highest subjective evaluation scores in terms of both quality and speaker similarity.

Advances in artificial intelligence (AI) will transform modern life by reshaping transportation, health, science, finance, and the military. To adapt public policy, we need to better anticipate these advances. Here we report the results from a large survey of machine learning researchers on their beliefs about progress in AI. Researchers predict AI will outperform humans in many activities in the next ten years, such as translating languages (by 2024), writing high-school essays (by 2026), driving a truck (by 2027), working in retail (by 2031), writing a bestselling book (by 2049), and working as a surgeon (by 2053). Researchers believe there is a 50% chance of AI outperforming humans in all tasks in 45 years and of automating all human jobs in 120 years, with Asian respondents expecting these dates much sooner than North Americans. These results will inform discussion amongst researchers and policymakers about anticipating and managing trends in AI. This article is part of the special track on AI and Society.

Most brain disorders are very heterogeneous in terms of their underlying biology and developing analysis methods to model such heterogeneity is a major challenge. A promising approach is to use probabilistic regression methods to estimate normative models of brain function using (f)MRI data then use these to map variation across individuals in clinical populations (e.g., via anomaly detection). To fully capture individual differences, it is crucial to statistically model the patterns of correlation across different brain regions and individuals. However, this is very challenging for neuroimaging data because of high-dimensionality and highly structured patterns of correlation across multiple axes. Here, we propose a general and flexible multi-task learning framework to address this problem. Our model uses a tensor-variate Gaussian process in a Bayesian mixed-effects model and makes use of Kronecker algebra and a low-rank approximation to scale efficiently to multi-way neuroimaging data at the whole brain level. On a publicly available clinical fMRI dataset, we show that our computationally affordable approach substantially improves detection sensitivity over both a mass-univariate normative model and a classifier that --unlike our approach-- has full access to the clinical labels.

Mobile US named Nokia to supply it with $3.5 billion in next-generation 5G network gear, the firms said on Monday, marking the world's largest 5G deal so far and concrete evidence of a new wireless upgrade cycle taking root. No.3 U.S. mobile carrier T-Mobile - which in April agreed to a merger with Sprint to create a more formidable rival to U.S. telecom giants Verizon and AT&T - said the multiyear supply deal with Nokia will deliver the first nationwide 5G services. The T-Mobile award is critical to Finland's Nokia, whose results have been battered by years of slowing demand for existing 4G networks and mounting investor doubts over whether 5G contracts can begin to boost profitability later this year. But cash-strapped telecom operators around the world have been gun-shy over committing to commercial upgrades of existing networks, with many seeing 5G technology simply as a way to deliver incremental capacity increases instead of new features. Advances in mobile data networks in the next decade could bring a number of benefits, according to the White House.

From the world's largest tech companies to start-ups, everyone is looking for people well-versed with Artificial Intelligence (AI). But a career in this business is no cakewalk: A lot of mathematics, constant leaning and understanding human behaviour are just some of the ways to get a foothold in this fast-growing industry. We spoke to five AI professionals, who tell us that a career in this field is about many different things, from data analysis, text and image recognition to linguistics--and no, evil robots do not figure in the list. AI researcher and founding member, Qure.ai Ghosh, 26, spends his days looking at X-rays. "I am almost a semi-radiologist.

Imagine you were traveling on business and you just arrived into town and had an emergency. Your luggage was sent to the wrong city or you were late for a critical meeting and you needed directions to the convention center. The check-in counter has a dozen guests waiting and the concierge is busy. Well, you may be in luck, because a four-foot robot with an open tablet computer and no waiting line is standing in the corner, and just may be able to come to your assistance. Pepper is an intelligent assistant that costs a bit more than a smart speaker, and can engage you in ways that go beyond ordering pizza or playing your favorite Top 40 tunes on the radio.

Recently I raised the question as to whether Google was ever going to make the leap from cloud pretender to cloud contender. One of the areas I felt it was playing second fiddle to Amazon is artificial intelligence (AI), but it's certainly trying to close that gap. Businesses of all sizes have been looking to the cloud to provide the infrastructure required to perform AI and machine learning (ML)-related tasks. Most organizations, particularly those just embarking on the AI/ML journey, don't have the necessary infrastructure or the skills. That is why so many companies have turned to cloud providers for their AI needs.

AI researchers have demonstrated a self-teaching algorithm that gives a robot hand remarkable new dexterity. Their creation taught itself to manipulate a cube with uncanny skill by practicing for the equivalent of a hundred years inside a computer simulation (though only a few days in real time). The robotic hand is still nowhere near as agile as a human one, and far too clumsy to be deployed in a factory or a warehouse. Even so, the research shows the potential for machine learning to unlock new robotic capabilities. It also suggests that some day robots might teach themselves new skills inside virtual worlds, which could greatly speed up the process of programming or training them.