Many sensors, such as range, sonar, radar, GPS and visual devices, produce measurements which are contaminated by outliers. This problem can be addressed by using fat-tailed sensor models, which account for the possibility of outliers. Unfortunately, all estimation algorithms belonging to the family of Gaussian filters (such as the widely-used extended Kalman filter and unscented Kalman filter) are inherently incompatible with such fat-tailed sensor models. The contribution of this paper is to show that any Gaussian filter can be made compatible with fat-tailed sensor models by applying one simple change: Instead of filtering with the physical measurement, we propose to filter with a pseudo measurement obtained by applying a feature function to the physical measurement. We derive such a feature function which is optimal under some conditions. Simulation results show that the proposed method can effectively handle measurement outliers and allows for robust filtering in both linear and nonlinear systems.

This paper proposes CF-NADE, a neural autoregressive architecture for collaborative filtering (CF) tasks, which is inspired by the Restricted Boltzmann Machine (RBM) based CF model and the Neural Autoregressive Distribution Estimator (NADE). We first describe the basic CF-NADE model for CF tasks. Then we propose to improve the model by sharing parameters between different ratings. A factored version of CF-NADE is also proposed for better scalability. Furthermore, we take the ordinal nature of the preferences into consideration and propose an ordinal cost to optimize CF-NADE, which shows superior performance. Finally, CF-NADE can be extended to a deep model, with only moderately increased computational complexity. Experimental results show that CF-NADE with a single hidden layer beats all previous state-of-the-art methods on MovieLens 1M, MovieLens 10M, and Netflix datasets, and adding more hidden layers can further improve the performance.

An augmented Lagrangian (AL) can convert a constrained optimization problem into a sequence of simpler (e.g., unconstrained) problems, which are then usually solved with local solvers. Recently, surrogate-based Bayesian optimization (BO) sub-solvers have been successfully deployed in the AL framework for a more global search in the presence of inequality constraints; however, a drawback was that expected improvement (EI) evaluations relied on Monte Carlo. Here we introduce an alternative slack variable AL, and show that in this formulation the EI may be evaluated with library routines. The slack variables furthermore facilitate equality as well as inequality constraints, and mixtures thereof. We show how our new slack "ALBO" compares favorably to the original. Its superiority over conventional alternatives is reinforced on several mixed constraint examples.

Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMs). HVMs augment a variational approximation with a prior on its parameters, which allows it to capture complex structure for both discrete and continuous latent variables. The algorithm we develop is black box, can be used for any HVM, and has the same computational efficiency as the original approximation. We study HVMs on a variety of deep discrete latent variable models. HVMs generalize other expressive variational distributions and maintains higher fidelity to the posterior.

Even if you think you know what cloud means, the word is fraught with too many different interpretations for too many people. Nevertheless, the effect of cloud computing, the web, and their assorted massive datacenters has had a profound impact on enterprise computing, creating new application segments and consolidating IT resources into a smaller number of mega-players with tremendous buying power and influence. At the top end of the market, ten companies – behemoths like Google, Amazon, eBay, and Alibaba – each spend over 1 billion per year on IT. These ten companies alone account for approximately 20 billion per year in IT consumption. Beyond that top tier, hundreds of additional companies complete the hyperscale landscape.

Ryan Brady is a digital strategist and social media manager for Digital Response Marketing Group. "Enjoy your com-FORT-able stay," says a robot front-desk clerk at Japan's Robot Hotel. Do you thank the robot for its awkward salutation? Or maybe you hesitate for a moment before shuffling off in silence. If our digital screens are separating us from human interaction, you better believe AI will further tear that tenuous social fabric.

It may be brilliant, but it's not all that trustworthy. That appears to be the opinion Americans hold when it comes to Artificial Intelligence systems. And while we may be interacting with AI systems more frequently than we realize (hi, Siri), a new study from Time etc suggests that Americans don't believe the AI revolution is quite here yet, with 54 percent claiming to have never interacted with such a system. While this proportion seems to speak mostly to the seamless integration of many such systems into our daily lives, the more interesting finding reveals that 26 percent of respondents said they would not trust an AI with any personal or professional task. Sure, sending a text message or making a phone call is fine, but 51 percent said they'd be uncomfortable sharing personal data with an AI system.

This book is an updated version of a well-received book previously published in Chinese by Science Press of China (the first edition in 2006 and the second in 2013). It offers a systematic and practical overview of spatial data mining, which combines computer science and geo-spatial information science, allowing each field to profit from the knowledge and techniques of the other. To address the spatiotemporal specialties of spatial data, the authors introduce the key concepts and algorithms of the data field, cloud model, mining view, and Deren Li methods. The cloud model is a qualitative method that utilizes quantitative numerical characters to bridge the gap between pure data and linguistic concepts. The mining view method discriminates the different requirements by using scale, hierarchy, and granularity in order to uncover the anisotropy of spatial data mining.

"Diversified application areas are expected to drive the artificial intelligence market" The artificial intelligence market is estimated to grow from USD 419.7 million in 2014 to USD 5.05 billion by 2020, at a CAGR of 53.65% from 2015 to 2020. This growth can be attributed to the factors such as diversified application areas, improved productivity, and increased customer satisfaction. "Machine learning technology to gain maximum traction during the forecast period" The machine learning technology is expected to account for the largest share of the overall AI market duing the forecast period. In addition, due to the increase in demand for AI from the media & advertising and finance sectors, the artificial intelligence market is expected to gain traction in the next five years. The machine learning technology market for the retail, healthcare, law, and oil & gas sectors is also expected to witness growth during the forecast period.

Artificial intelligence (AI) is attracting a lot of attention this year as it moves beyond background automation into consumer-facing roles. Rainbird co-founder and chairman James Duez believes this is just a natural evolution of what's come before. Here he talks about the social impacts of this increasing automation and why a general AI is still a long way off. Can you explain the difference between decision tree bots and the kind of AI Rainbird uses? Decision trees won't learn about me from our interaction and won't be able to take new questions in context. It will not understand the question, "What if I turn GPS off?" if my first question was how to make my phone battery last longer.