Editor's note: We sat down with data scientist and artificial intelligence evangelist Ozge Yeloglu to talk about her love of machine learning and how she battles perfectionism. This story is told in her own words. On my first day of college classes at Ege University in Turkey, I sat down in the computer lab and was instructed to insert the floppy disk. I stared blankly at the computer, because I had no idea what a floppy disk was or how to put it in correctly. I quickly looked over at the kids next to me and watched what they did.

In this paper, we propose a variant of Answer Set Programming (ASP) with evaluable functions that extends their application to sets of objects, something that allows a fully logical treatment of aggregates. Formally, we start from the syntax of First Order Logic with equality and the semantics of Quantified Equilibrium Logic with evaluable functions (QELF). Then, we proceed to incorporate a new kind of logical term, intensional set (a construct commonly used to denote the set of objects characterised by a given formula), and to extend QELF semantics for this new type of expression. In our extended approach, intensional sets can be arbitrarily used as predicate or function arguments or even nested inside other intensional sets, just as regular first-order logical terms. As a result, aggregates can be naturally formed by the application of some evaluable function (count, sum, maximum, etc) to a set of objects expressed as an intensional set. This approach has several advantages. First, while other semantics for aggregates depend on some syntactic transformation (either via a reduct or a formula translation), the QELF interpretation treats them as regular evaluable functions, providing a compositional semantics and avoiding any kind of syntactic restriction. Second, aggregates can be explicitly defined now within the logical language by the simple addition of formulas that fix their meaning in terms of multiple applications of some (commutative and associative) binary operation. For instance, we can use recursive rules to define sum in terms of integer addition. Last, but not least, we prove that the semantics we obtain for aggregates coincides with the one defined by Gelfond and Zhang for the Alog language, when we restrict to that syntactic fragment. (Under consideration for acceptance in TPLP)

Negotiation is a very common interaction between automated agents. Many common negotiation protocols work with cardinal utilities, even though ordinal preferences, which only rank the outcomes, are easier to elicit from humans. In this work we concentrate on negotiation with ordinal preferences over a finite set of outcomes. We study an intuitive protocol for bilateral negotiation, where the two parties make offers alternately. We analyze the negotiation protocol under different settings. First, we assume that each party has full information about the other party's preference order. We provide elegant strategies that specify a sub-game perfect equilibrium for the agents. We further show how the studied negotiation protocol almost completely implements a known bargaining rule. Finally, we analyze the no information setting. We study several solution concepts that are distribution-free, and analyze both the case where neither party knows the preference order of the other party, and the case where only one party is uninformed.

The continuous dimensional emotion modelled by arousal and valence can depict complex changes of emotions. In this paper, we present our works on arousal and valence predictions for One-Minute-Gradual (OMG) Emotion Challenge. Multimodal representations are first extracted from videos using a variety of acoustic, video and textual models and support vector machine (SVM) is then used for fusion of multimodal signals to make final predictions. Our solution achieves Concordant Correlation Coefficient (CCC) scores of 0.397 and 0.520 on arousal and valence respectively for the validation dataset, which outperforms the baseline systems with the best CCC scores of 0.15 and 0.23 on arousal and valence by a large margin.

Chinese pinyin input methods are very important for Chinese language processing. Actually, users may make typos inevitably when they input pinyin. Moreover, pinyin typo correction has become an increasingly important task with the popularity of smartphones and the mobile Internet. How to exploit the knowledge of users typing behaviors and support the typo correction for acronym pinyin remains a challenging problem. To tackle these challenges, we propose KNPTC, a novel approach based on neural machine translation (NMT). In contrast to previous work, KNPTC is able to integrate explicit knowledge into NMT for pinyin typo correction, and is able to learn to correct a variety of typos without the guidance of manually selected constraints or languagespecific features. In this approach, we first obtain the transition probabilities between adjacent letters based on large-scale real-life datasets. Then, we construct the "ground-truth" alignments of training sentence pairs by utilizing these probabilities. Furthermore, these alignments are integrated into NMT to capture sensible pinyin typo correction patterns. KNPTC is applied to correct typos in real-life datasets, which achieves 32.77% increment on average in accuracy rate of typo correction compared against the state-of-the-art system.

Abstract--Accurate Traffic Sign Detection (TSD) can help intelligent systems make better decisions according to the traffic regulations. TSD, regarded as a typical small object detection problem in some way, is fundamental in Advanced Driver Assistance Systems (ADAS) and self-driving. However, although deep neural networks have achieved human even superhuman performance on several tasks, due to their own limitations, small object detection is still an open question. In this paper, we proposed a brain-inspired network, named as KB-RANN, to handle this problem. Attention mechanism is an essential function of our brain, we used a novel recurrent attentive neural network to improve the detection accuracy in a fine-grained manner . Further, we combined domain specific knowledge and intuitive knowledge to improve the efficiency. Experimental result shows that our methods achieved better performance than several popular methods widely used in object detection. More significantly, we transplanted our method on our designed embedded system and deployed on our self-driving car successfully. With the help of powerful well-designed deep neural networks, great progresses have been made in the field of object detection [1], [2].

We propose two spectral algorithms for partitioning nodes in directed graphs respectively with a cyclic and an acyclic pattern of connection between groups of nodes. Our methods are based on the computation of extremal eigenvalues of the transition matrix associated to the directed graph. The two algorithms outperform state-of-the art methods for directed graph clustering on synthetic datasets, including methods based on blockmodels, bibliometric symmetrization and random walks. Our algorithms have the same space complexity as classical spectral clustering algorithms for undirected graphs and their time complexity is also linear in the number of edges in the graph. One of our methods is applied to a trophic network based on predator-prey relationships. It successfully extracts common categories of preys and predators encountered in food chains. The same method is also applied to highlight the hierarchical structure of a worldwide network of Autonomous Systems depicting business agreements between Internet Service Providers.

The rise of the machines has well and truly started. Data from the International Federation of Robotics reveals that the pace of industrial automation is accelerating across much of the developed world with 66 installed industrial robots per 10,000 employees globally in 2015. A year later, that increased to 74. Europe has a robot density of 99 units per 10,000 workers and that number is 84 and 63 in the Americas and Asia respectively. China is one of the countries recording the highest growth levels in industrial automation but nowhere has a robot density like South Korea.

What if traffic lights turned red or green at the optimal time? What if a robot could clean up after your kids? What if the city could monitor railroad tracks in real time, preventing collisions between people and trains? These scenarios and similar ones are not too far in the future, according to experts at Tel Aviv University, where scientists and other researchers are working on several machine learning (ML) and artificial intelligence (AI) projects.

Dhaka, April 15 (UNB)- Huawei, world's leading ICT solutions provider, has recently showcased its smart airport ICT solutions under the theme of "Leading New ICT, The Road to Digital Aviation" at the Passenger Terminal EXPO 2018. More than 7,000 delegates and 225 exhibitors represented the worldwide aviation ecosystem in the exhibition to discuss the latest developments and innovations. Yuan Xilin, President of the Transportation Sector of Huawei Enterprise BG, said in Huawei Global Aviation Summit 2018, "The concept of a smart airport is now becoming a reality around the world as airports adopt innovative ICT which enables digital and visualized flight services, passenger services, and airport operations." "Huawei's solution is based on new ICT such as cloud, Internet of Things (IoT), Artificial Intelligence (AI) and cloud-pipe-device collaboration that help to build future-oriented smart airports", he said. "We aim to bring significant benefits to customers in terms of safety assurance, airport operational efficiency and service quality by creating the best-in-class travel experience for global passengers", he added.