Reaching a new milestone in its quest to achieve speed and scalability in indexing and exploiting vast amounts of video, IDENTV announced today the beta release of Neural Upscaling, its proprietary solution for dramatically enhancing image quality, allowing for significantly greater accuracy in object and facial recognition. "This capability automates the process of enhancing quality of a degraded image and amplifies the original with 400% more detail thus enabling rapid detection and matching of objects and faces that was previously not possible at speed and scale," explained Mohamad Shihadah, founder and CEO of IDENTV. Neural Upscaling is an integral part of IDENTV's pioneering Intelligent Video-fingerprinting Platform (IVP), a technology that combines artificial intelligence, machine learning, and computer vision in a highly integrated fashion to deliver high-speed visual content recognition and indexing. Neural Upscaling has broad applications across commercial and national security applications and solves a critical limitation on video, faces, or objects that are degraded. IDENTV was recently selected as one of the Top 5 Artificial Intelligence companies in the DC area.

Revision wars on Wikipedia amongst human editors is an all-too-common occurrence, but new research from the UK shows that similar online battles are being waged between the site's software robots. As a new study published in PLOS ONE reveals, Wikipedia's bots don't always get along, frequently undoing each other's edits. These online algorithms, each equipped with their own instructions and goals, engage in sterile "fights" over content that can persist for years. The new research shows how relatively "dumb" bots can produce complex interactions and behaviors, and how developers need to stay on top of their digital creations. This has implications not just for the quality of Wikipedia pages, but for the development of AI in general--particularly any autonomous agents set loose on the web.

You can add the cult classic Super Smash Bros Melee to the list of games soon to be dominated by AIs. Research at MIT's Computer Science and Artificial Intelligence Laboratory has produced a computer player superior to the drones you can already fight in the game. It's good enough that it held its own against globally-ranked players. Its cutesy appearance belies its strategic depth: "The SSBM environment has complex dynamics and partial observability, making it challenging for human and machine alike. The multiplayer aspect poses an additional challenge," reads the paper's abstract.

A new study has found that humans aren't the only one's fighting about Wikipedia revisions. Researchers have discovered that software robots designed to improve articles on the site were'fighting' over content and undoing each other's edits for 10 years. The findings have shown that even simple autonomous algorithms can produce complex interactions that result in unintended consequences. Researchers discovered that software robots designed to improve articles on Wikipedia were'fighting' over content and undoing each other's edits for 10 years. Researchers have discovered that software robots designed to improve articles on Wikipedia have been'fighting' over content and undoing each other's edits.

Open forms of global constraints allow the addition of new variables to an argument during the execution of a constraint program. Such forms are needed for difficult constraint programming problems where problem construction and problem solving are interleaved, and fit naturally within constraint logic programming. However, in general, filtering that is sound for a global constraint can be unsound when the constraint is open. This paper provides a simple characterization, called contractibility, of the constraints where filtering remains sound when the constraint is open. With this characterization we can easily determine whether a constraint has this property or not. In the latter case, we can use it to derive a contractible approximation to the constraint. We demonstrate this work on both hard and soft constraints. In the process, we formulate two general classes of soft constraints.

With a rapidly increasing number of devices connected to the internet, big data has been applied to various domains of human life. Nevertheless, it has also opened new venues for breaching users' privacy. Hence it is highly required to develop techniques that enable data owners to privatize their data while keeping it useful for intended applications. Existing methods, however, do not offer enough flexibility for controlling the utility-privacy trade-off and may incur unfavorable results when privacy requirements are high. To tackle these drawbacks, we propose a compressive-privacy based method, namely RUCA (Ratio Utility and Cost Analysis), which can not only maximize performance for a privacy-insensitive classification task but also minimize the ability of any classifier to infer private information from the data. Experimental results on Census and Human Activity Recognition data sets demonstrate that RUCA significantly outperforms existing privacy preserving data projection techniques for a wide range of privacy pricings.

Deep neural networks have achieved state-of-the-art performance on many machine learning tasks in areas such as natural language processing (Wu et al., 2016), computer vision (Krizhevsky et al., 2012) and speech recognition (Hinton et al., 2012). Training of such networks is often successfully performed by minimizing a high-dimensional non-convex objective function, using simple first-order methods such as stochastic gradient descent. Nonetheless, the success of deep learning from an optimization perspective is poorly understood theoretically. Current results are mostly pessimistic, suggesting that even training a 3-node neural network is NPhard (Blum & Rivest, 1993), and that the objective function of a single neuron can admit exponentially many local minima (Auer et al., 1996; Safran & Shamir, 2016). There have been recent attempts to bridge this gap between theory and practice.

We develop and analyze efficient "coordinate-wise" methods for finding the leading eigenvector, where each step involves only a vector-vector product. We establish global convergence with overall runtime guarantees that are at least as good as Lanczos's method and dominate it for slowly decaying spectrum. Our methods are based on combining a shift-and-invert approach with coordinate-wise algorithms for linear regression.

Boolean matrix factorisation aims to decompose a binary data matrix into an approximate Boolean product of two low rank, binary matrices: one containing meaningful patterns, the other quantifying how the observations can be expressed as a combination of these patterns. We introduce the OrMachine, a probabilistic generative model for Boolean matrix factorisation and derive a Metropolised Gibbs sampler that facilitates efficient parallel posterior inference. On real world and simulated data, our method outperforms all currently existing approaches for Boolean matrix factorisation and completion. This is the first method to provide full posterior inference for Boolean Matrix factorisation which is relevant in applications, e.g. for controlling false positive rates in collaborative filtering and, crucially, improves the interpretability of the inferred patterns. The proposed algorithm scales to large datasets as we demonstrate by analysing single cell gene expression data in 1.3 million mouse brain cells across 11 thousand genes on commodity hardware.

We consider the problem of optimal budget allocation for crowdsourcing problems, allocating users to tasks to maximize our final confidence in the crowdsourced answers. Such an optimized worker assignment method allows us to "boost" the efficacy of any popular crowdsourcing estimation algorithm. We consider a mutual information interpretation of the crowdsourcing problem, which leads to a stochastic subset selection problem with a submodular objective function. We present experimental simulation results which demonstrate the effectiveness of our dynamic task allocation method for achieving higher accuracy, possibly requiring fewer labels, as well as improving upon a previous method which is sensitive to the proportion of users to questions.