Predicting the risk of potential diseases from Electronic Health Records (EHR) has attracted considerable attention in recent years, especially with the development of deep learning techniques. Compared with traditional machine learning models, deep learning based approaches achieve superior performance on risk prediction task. However, none of existing work explicitly takes prior medical knowledge (such as the relationships between diseases and corresponding risk factors) into account. In medical domain, knowledge is usually represented by discrete and arbitrary rules. Thus, how to integrate such medical rules into existing risk prediction models to improve the performance is a challenge.

Machine learning (ML) systems have been increasingly applied in web security applications such as spammer detection, malware detection and fraud detection. These applications have an intrinsic adversarial nature where intelligent attackers can adaptively change their behaviors to avoid being detected by the deployed detectors. Existing efforts against adversaries are usually limited by the type of applied ML models or the specific applications such as image classification. Additionally, the working mechanisms of ML models usually cannot be well understood by users, which in turn impede them from understanding the vulnerabilities of models nor improving their robustness. To bridge the gap, in this paper, we propose to investigate whether model interpretation could potentially help adversarial detection.

Learning-based hashing has recently received considerable attentions due to its capability of supporting efficient storage and retrieval of high-dimensional data such as images, videos, and documents. In this paper, we propose a learning-based hashing algorithm called "Robust Rotated Supervised Discrete Hashing" (R 2 SDH), by extending the previous work on "Supervised Discrete Hashing" (SDH). In R 2 SDH, correntropy is adopted to replace the least square regression (LSR) model in SDH for achieving better robustness. Furthermore, considering the commonly used distance metrics such as cosine and Euclidean distance are invariant to rotational transformation, rotation is integrated into the original zero-one label matrix used in SDH, as additional freedom to promote flexibility without sacrificing accuracy. The rotation matrix is learned through an optimization procedure.

Professor Toby Walsh, one of the leading researchers in Artificial Intelligence, has in one-hour long public debate with Franz Zeller (ORF) talked about how AI has been improving our lives, and why the society needs to be economically, culturally, politically and legally prepared for the AI of tomorrow. This event was part of the LogicLounge public discussion series, organized by Vienna Center for Logic and Algorithms at TU Wien.

Deep neural networks are a powerful method for automatically learning distributed representations at multiple levels of abstraction. Over the past decade, they have dramatically pushed forward the state-of-the-art in domains as diverse as vision, language understanding, robotics, game playing, graphics, health care, and genomics. The Deep Learning Summer School (DLSS) covers both the foundations and applications of deep neural networks, from fundamental concepts to cutting-edge research results.

We are excited to announce the release of the Deep Learning and Reinforcement Learning Summer School videos!

The relation between mostly concept-based lexical-semantic networks (wordnets) and lemma-based lexical resources (dictionaries) has been explored so far mainly for wordnet-building purposes, and such projects and related issues are well documented. In spite of not being meant to serve lexicographical purposes (in the case of most wordnets, with some notable exceptions), wordnets have become a de facto standard for the drafting of dictionary content. Experience resulting from using wordnets as a data source for lexicography and issues related to them have just started to be systematically discussed. In the WNLEX Workshop, we define the state of the art in the discussed topics, provide a survey of solved and unsolved issues, and an outlook on future work regarding wordnet as a resource in lexicographical workflows. Target group for this workshop is lexicographers.

The goal of the Semantic Web is to create a Web of knowledge and services in which the semantics of content is made explicit and content is linked to both other content and services allowing novel applications to combine content from heterogeneous sites in unforeseen ways and support enhanced matching between users needs and content. This network of knowledge-based functionality will weave together a large network of human knowledge, and make this knowledge machine-processable to support intelligent behaviour by machines. Creating such an interlinked Web of knowledge which spans unstructured text, structured data (e.g. RDF) as well as multimedia content and services requires the collaboration of many disciplines, including but not limited to: Artificial Intelligence, Natural Language Processing, Databases and Information Systems, Information Retrieval, Machine Learning, Multimedia, Distributed Systems, Social Networks, Web Engineering, and Web Science.

JOTA talks organized by SDJT - Slovensko društvo za jezikovne tehnologije hosted Dr Ruslan Mitkov, a Professor of Computational Linguistics and Language Engineering at the University of Wolverhampton, who gave a talk on anaphora and coreference resolution.

The morphogenesis of branched organs remains a subject of abiding interest. Although much is known about the underlying signaling pathways, it remains unclear how macro-scopic features of branched organs, including their size, network topology, and spatial patterning, are encoded. Here, we show that, in mouse mammary gland, kidney, and hu-man prostate, these features can be explained quantitatively within a single unifying framework of branching and annihilating random walks. Based on quantitative analyses of large-scale organ reconstructions and proliferation kinetics measurements, we propose that morphogenesis follows from the proliferative activity of equipotent tips that stochas-tically branch and randomly explore their environment but compete neutrally for space, becoming proliferatively inactive when in proximity with neighboring ducts. These results show that complex branched epithelial structures develop as a self-organized process, reliant upon a strikingly simple but generic rule, without recourse to a rigid and determin-istic sequence of genetically programmed events.