W e propose a new framework for the analysis of low-rank tensors which lies at the intersection of spectral graph theory and signal processing. As a first step, we present a new graph based low-rank decomposition which approximates the classical low-rank SVD for matrices and multi-linear SVD for tensors. Then, building on this novel decomposition we construct a general class of convex optimization problems for approximately solving low-rank tensor inverse problems, such as tensor Robust PCA. The whole framework is named as "Multilinear Low-rank tensors on Graphs (MLRTG)". Our theoretical analysis shows: 1) MLRTG stands on the notion of approximate stationarity of multidimensional signals on graphs and 2) the approximation error depends on the eigen gaps of the graphs. W e demonstrate applications for a wide variety of 4 artificial and 12 real tensor datasets, such as EEG, FMRI, BCI, surveillance videos and hyperspectral images. Generalization of the tensor concepts to non-euclidean domain, orders of magnitude speedup, low-memory requirement and significantly enhanced performance at low SNR are the key aspects of our framework.

A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored. We analyze this heuristic and show that with carefully chosen parameters and noise injection, this method can provably evade saddle points. We establish the convergence of NGD to a local minimum, and demonstrate rates which improve upon the fastest known first order algorithm due to Ge e al. (2015). The effectiveness of our method is demonstrated via an application to the problem of online tensor decomposition; a task for which saddle point evasion is known to result in convergence to global minima.

The ability to track a moving vehicle is of crucial importance in numerous applications. The task has often been approached by the importance sampling technique of particle filters due to its ability to model non-linear and non-Gaussian dynamics, of which a vehicle travelling on a road network is a good example. Particle filters perform poorly when observations are highly informative. In this paper, we address this problem by proposing particle filters that sample around the most recent observation. The proposal leads to an order of magnitude improvement in accuracy and efficiency over conventional particle filters, especially when observations are infrequent but low-noise.

A probabilistic query may not be estimable from observed data corrupted by missing values if the data are not missing at random (MAR). It is therefore of theoretical interest and practical importance to determine in principle whether a probabilistic query is estimable from missing data or not when the data are not MAR. We present an algorithm that systematically determines whether the joint probability is estimable from observed data with missing values, assuming that the data-generation model is represented as a Bayesian network containing unobserved latent variables that not only encodes the dependencies among the variables but also explicitly portrays the mechanisms responsible for the missingness process.

New proposed models are often compared to state-of-the-art using statistical significance testing. Literature is scarce for classifier comparison using metrics other than accuracy. We present a survey of statistical methods that can be used for classifier comparison using precision, accounting for inter-precision correlation arising from use of same dataset. Comparisons are made using per-class precision and methods presented to test global null hypothesis of an overall model comparison. Comparisons are extended to multiple multi-class classifiers and to models using cross validation or its variants. Partial Bayesian update to precision is introduced when population prevalence of a class is known. Applications to compare deep architectures are studied.

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.

The social robot startup Jibo has raised $13.1 million from investors, but a filing with the Securities and Exchange Commission shows the company is looking to raise a total of $28 million.

Lower and middle-skilled roles, such as routine manual or data processing jobs, are at risk from developing AI, according to a report published by the Government Office for Science. Outlining some of the possible implications of AI, the report says new technologies such as machine learning, robotics, big data and autonomous systems could have huge implications for the economy and labour markets. It reads: "These technologies together can be seen as part of a new wave of'general purpose' digital technologies, comparable to the steam engine, and the moving assembly line, with the potential to drive significant socio-economic change." The extent and speed at which new technologies will impact the labour market is still uncertain, however. While a Deloitte study quoted by the report found that 35% of UK jobs will be affected by automation over the next 10 to 20 years, the OECD said only 10% of jobs are at risk.

Samsung Electronics Co. is making a drive for control of the car. The South Korean smartphone maker said Monday that it would buy U.S. auto-parts supplier Harman International Industries Inc., based in Stamford, Conn., for $8 billion in an all-cash deal that instantly makes Samsung a major player in the world of automotive technology. The deal -- Samsung's biggest acquisition in its history -- reshapes the pecking order in the global automotive supply chain, reflecting a quickening pace of innovation and an increased role for companies with deep pockets and a keen understanding of mobile services. Harman, an audio pioneer that dates back to 1953, has in recent years pushed aggressively into the automotive world under CEO Dinesh Paliwal, and has secured billions in new business, including big contracts with General Motors Co. and Fiat Chrysler Automobiles NV. It has projected an order backlog of $24 billion, more than three times annual revenue, and about two-thirds of its current sales come from auto makers.

BenevolentAI has acquired an exclusive licence for the novel clinical stage candidates, having first used its AI technology to assess their potential. It continues the firm's move into territory more often associated with IT heavyweights like Google and its DeepMind Health unit or IBM and its Watson technology. BenevolentAI's deal with J&J's Janssen Pharmaceutica NV company focuses on hard to treat diseases and will allow it to select a number of small molecule compounds, along with their patent portfolio. BenevolentAI will then have the sole right to develop, manufacture and commercialise these novel drug candidates in all indications and in all territories. The London-based firm said the agreement would enable it to accelerate its development pipeline and use its artificial intelligence technology to provide a rich source of clinical data.