Many data mining tasks cannot be completely addressed by automated processes, such as sentiment analysis and image classification. Crowdsourcing is an effective way to harness the human cognitive ability to process these machine-hard tasks. Thanks to public crowdsourcing platforms, e.g., Amazon Mechanical Turk and CrowdFlower, we can easily involve hundreds of thousands of ordi- nary workers (i.e., the crowd) to address these machine-hard tasks. In this tutorial, we will survey and synthesize a wide spectrum of existing studies on crowd-powered data mining. We rst give an overview of crowdsourcing, and then summarize the fundamental techniques, including quality control, cost control, and latency control, which must be considered in crowdsourced data mining. Next we review crowd-powered data mining operations, including classification, clustering, pattern mining, outlier detection, knowledge base construction and enrichment. Finally, we provide the emerging challenges in crowdsourced data mining.

With the world moving towards being increasingly dependent on computers and automation, one of the main challenges in the current decade has been to build secure applications, systems and networks. Alongside these challenges, the number of threats is rising exponentially due to the attack surface increasing through numerous interfaces offered for each service. To alleviate the impact of these threats, researchers have proposed numerous solutions; however, current tools often fail to adapt to ever-changing architectures, associated threats and 0-days. This manuscript aims to provide researchers with a taxonomy and survey of current dataset composition and current Intrusion Detection Systems (IDS) capabilities and assets. These taxonomies and surveys aim to improve both the efficiency of IDS and the creation of datasets to build the next generation IDS as well as to reflect networks threats more accurately in future datasets. To this end, this manuscript also provides a taxonomy and survey or network threats and associated tools. The manuscript highlights that current IDS only cover 25% of our threat taxonomy, while current datasets demonstrate clear lack of real-network threats and attack representation, but rather include a large number of deprecated threats, hence limiting the accuracy of current machine learning IDS. Moreover, the taxonomies are open-sourced to allow public contributions through a Github repository.

What are some underdeveloped areas in computer science research right now (2018)? Over the past few decades, computer science research, either in industry or academia, has led to ground breaking technology innovations such as the internet, which continues to change our lives. In the post-Moore's Law era, advances in cloud computing affected so many sub-areas of computer science like operating systems and database systems. Furthermore, solid state drives (SSDs) changed the way we design storage systems, which were previously tailored for the mechanical hard drive (HDD). Recently, quantum computing promises lightning-speed calculations as opposed to classic electronics-based computers.

Dating and romantic relationships not only play a huge role in our personal lives but also collectively influence and shape society. Today, many romantic partnerships originate from the Internet, signifying the importance of technology and the web in modern dating. In this paper, we present a text-based computational approach for estimating the relationship compatibility of two users on social media. Unlike many previous works that propose reciprocal recommender systems for online dating websites, we devise a distant supervision heuristic to obtain real world couples from social platforms such as Twitter. Our approach, the CoupleNet is an end-to-end deep learning based estimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users. Intuitively, our approach performs both user profiling and match-making within a unified end-to-end framework. CoupleNet utilizes hierarchical recurrent neural models for learning representations of user profiles and subsequently coupled attention mechanisms to fuse information aggregated from two users. To the best of our knowledge, our approach is the first data-driven deep learning approach for our novel relationship recommendation problem. We benchmark our CoupleNet against several machine learning and deep learning baselines. Experimental results show that our approach outperforms all approaches significantly in terms of precision. Qualitative analysis shows that our model is capable of also producing explainable results to users.

By Will Yang Technology in today's day and age has enabled a human to do things and accomplish far more than one could think of a few years back. Thanks to rapidly evolving and innovative technologies, personal lives have become more enriched. Meaningful collaborations between a human and machine/technology has in many ways provided a wealth of opportunities to us making our lives comfortable. One such technology buzzword in the industry today is Artificial Intelligence. Once a topic for science fiction, Artificial Intelligence technology is now being used by brands across industries and categories.

The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNN) in creating artistic imagery by separating and recombining image content and style. This process of using CNN to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. This review aims to provide an overview of the current progress towards NST, as well as discussing its various applications and open problems for future research.

Over the past years, distributed representations have proven effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey is focused on semantic representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their main limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and provides an analysis of five important aspects: interpretability, sense granularity, adaptability to different domains, compositionality and integration into downstream applications.

A few weeks ago, I attempted to sit through Samsung's live-streamed Galaxy S9 smartphone launch event. I nearly fell asleep at my desk. Or the relocated fingerprint sensor, which is exactly what it sounds like. I realize this is a first-world problem, but in the 11 years since the release of the iPhone, advances in personal technology have gone from breakthrough to, well, pretty broke. What--and where--is the next revolutionary product, the thing that rewrites the rules and alters our lives forever?

Springer Nature, the publisher of Scientific American and the venerable scientific journal Nature, intends to stride into the white-hot field of machine learning in early 2019 with a new journal called Nature Machine Intelligence. But the community of machine learning researchers, which prides itself on publishing to open-access journals, was immediately put off by the idea of a closed-access journal that requires academic credentials to read. Thomas Dietterich, the former executive editor of the journal Machine Learning and an emeritus professor of computer science at Oregon State University, posted a pledge not to submit, review or edit for Nature Machine Intelligence, and invited other researchers in the field to sign the pledge as well. At the time of writing, the boycott had accumulated more than 2,400 signatures by employees of Google, Facebook, IBM, Harvard, MIT and a cross-section of other prominent institutions--as well as many of the biggest names in artificial intelligence research including neural network pioneers Yann LeCun and Yoshua Bengio and Google Brain co-founder Jeff Dean. "We write the papers, we copyedit the papers, we typeset the papers, and we review the papers," Dietterich told Motherboard in an email.

In this special guest feature, Geoff Tudor, VP and GM of Cloud Data Services at Panzura, believes AI poses both opportunities and risks in the automation of the datacenter. This article provides an overview regarding the impact of AI in the datacenter, and how companies can prepare their storage infrastructure for these technologies. Geoff has over 22 years experience in storage, broadband, and networking. As Chief Cloud Strategist at Hewlett Packard Enterprise, Geoff led CxO engagements for Fortune 100 private cloud opportunities resulting in 10X growth to over $1B in revenues while positioning HPE as the #1 private cloud infrastructure supplier globally. Geoff holds an MBA from The University of Texas at Austin, a BA from Tulane University, and is a patent-holder in satellite communications.