Sensor-based activity recognition seeks the profound high-level knowledge about human activities from multitudes of low-level sensor readings. Conventional pattern recognition approaches have made tremendous progress in the past years. However, those methods often heavily rely on heuristic hand-crafted feature extraction, which could hinder their generalization performance. Additionally, existing methods are undermined for unsupervised and incremental learning tasks. Recently, the recent advancement of deep learning makes it possible to perform automatic high-level feature extraction thus achieves promising performance in many areas. Since then, deep learning based methods have been widely adopted for the sensor-based activity recognition tasks. This paper surveys the recent advance of deep learning based sensor-based activity recognition. We summarize existing literature from three aspects: sensor modality, deep model, and application. We also present detailed insights on existing work and propose grand challenges for future research.

The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced deep Echo State Network (deepESN) model opened the way to an extremely efficient approach for designing deep neural networks for temporal data. At the same time, the study of deepESNs allowed to shed light on the intrinsic properties of state dynamics developed by hierarchical compositions of recurrent layers, i.e. on the bias of depth in RNNs architectural design. In this paper, we summarize the advancements in the development, analysis and applications of deepESNs.

This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in painting results. We propose using exemplar information in the form of a reference image of the region to in-paint, or a perceptual code describing that object. Unlike previous conditional GAN formulations, this extra information can be inserted at multiple points within the adversarial network, thus increasing its descriptive power. We show that ExGANs can produce photo-realistic personalized in-painting results that are both perceptually and semantically plausible by applying them to the task of closed to-open eye in-painting in natural pictures. A new benchmark dataset is also introduced for the task of eye in-painting for future comparisons.

Two leading Chinese tech companies, internet giant Baidu Inc and consumer electronics company Xiaomi Corp, announced collaboration to develop Artificial Intelligence (AI) and the Internet of Things (IoT). This partnership can lead to a massive expansion of innovative technologies and change the manufacturing industry. Xiaomi has already created remarkable core competence in IoT: according to the latest estimation their smart hardware platform connects more than 85 million connected devices. This company is also developing AI: this year its abilities in this sphere became evident with the launch of the Mi AI Speaker. Baidu is a recognized AI leader well-known for its conversational AI system DuerOS aimed at IoT They claim that more than 130 companies all over the world are already using their technologies. The strategic partnership of these companies is seen as perspective cooperation that can make the most of AI and IoT interaction.

COMMANDING the plot lines of Hollywood films, covers of magazines and reams of newsprint, the contest between artificial intelligence (AI) and mankind draws much attention. Doomsayers warn that AI could eradicate jobs, break laws and start wars. The competition today is not between humans and machines but among the world's technology giants, which are investing feverishly to get a lead over each other in AI. An exponential increase in the availability of digital data, the force of computing power and the brilliance of algorithms has fuelled excitement about this formerly obscure corner of computer science. The West's largest tech firms, including Alphabet (Google's parent), Amazon, Apple, Facebook, IBM and Microsoft are investing huge sums to develop their AI capabilities, as are their counterparts in China. Although it is difficult to separate tech firms' investments in AI from other kinds, so far in 2017 (see chart 1) companies globally have completed around $21.3bn in mergers and acquisitions related to AI, according to PitchBook, a data provider, or around 26 times more than in 2015.

Recommenders have become widely popular in recent years because of their broader applicability in many e-commerce applications. These applications rely on recommenders for generating advertisements for various offers or providing content recommendations. However, the quality of the generated recommendations depends on user features (like demography, temporality), offer features (like popularity, price), and user-offer features (like implicit or explicit feedback). Current state-of-the-art recommenders do not explore such diverse features concurrently while generating the recommendations. In this paper, we first introduce the notion of Trackers which enables us to capture the above-mentioned features and thus incorporate users' online behaviour through statistical aggregates of different features (demography, temporality, popularity, price). We also show how to capture offer-to-offer relations, based on their consumption sequence, leveraging neural embeddings for offers in our Offer2Vec algorithm. We then introduce BoostJet, a novel recommender which integrates the Trackers along with the neural embeddings using MatrixNet, an efficient distributed implementation of gradient boosted decision tree, to improve the recommendation quality significantly. We provide an in-depth evaluation of BoostJet on Yandex's dataset, collecting online behaviour from tens of millions of online users, to demonstrate the practicality of BoostJet in terms of recommendation quality as well as scalability.

There are multiple ways to classify data with machine learning. You could run a logistic regression, use decision trees, or build a neural network to accomplish the task. In 1963, Vladimir Vapnik and Alexey Chervonenkis developed another classification tool, the support vector machine. Vapnik refined this classification method in the 1990's and extended uses for SVMs. Support vector machines have become a great tool for the data scientist.

While convergence of the Alternating Direction Method of Multipliers (ADMM) on convex problems is well studied, convergence on nonconvex problems is only partially understood. In this paper, we consider the Gaussian phase retrieval problem, formulated as a linear constrained optimization problem with a biconvex objective. The particular structure allows for a novel application of the ADMM. It can be shown that the dual variable is zero at the global minimizer. This motivates the analysis of a block coordinate descent algorithm, which is equivalent to the ADMM with the dual variable fixed to be zero. We show that the block coordinate descent algorithm converges to the global minimizer at a linear rate, when starting from a deterministically achievable initialization point.

Algorithms will be as important as ammunition in the future of warfare, according to a new report. The US armed services invested $7.4 billion (£5.5bn) in AI, big data and cloud computing last year which is set to change modern warfare, the report revealed. Military chiefs have warned the US'can either lead the coming revolution, or fall victim to it'. The report comes as the Pentagon focuses on improving its algorithms amid growing concern powerful Chinese and Russian AI could be set on world domination. The US armed services invested $7.4 billion ($5.5bn) in AI, big data and cloud computing last year which is set to change modern warfare, the report revealed.

"The time is ripe, even overdue, to take a cold, hard look at what a highly disruptive technology could do to the industry." From the design and construction of a building through to managing and maintaining it, artificial intelligence (AI) is increasingly being integrated into core business strategies and impacting the work of surveyors of all disciplines and their fellow professionals. This paper examines the current thinking, state-of-the-art applications and predictions surrounding AI to uncover many examples of how it will transform the way we work and how we can exploit it to improve the quality of the built environment. Decades of steady and sometimes staggering improvements in technology has changed how most of us do our work and interact with others. For those engaged in creating and sustaining the built environment, there are threats from AI that can increasingly outperform the physical and cognitive skills of workers on all levels.