Members of Rajat Monga's team at Google will be teaching tutorials on deep learning with TensorFlow at Strata Hadoop World in Beijing (August 4th) and NYC (September 27th). Subscribe to the O'Reilly Data Show Podcast to explore the opportunities and techniques driving big data and data science. Find us on Stitcher, TuneIn, iTunes, SoundCloud, RSS. In this episode of the O'Reilly Data Show, I spoke with Rajat Monga, who serves as a director of engineering at Google and manages the TensorFlow engineering team. We talked about how he ended up working on deep learning, the current state of TensorFlow, and the applications of deep learning to products at Google and other companies. There's not going to be too many areas left that run without machine learning that you can program.

SAN FRANCISCO – In a few weeks, Uber will start using self-driving cars to carry passengers in Pittsburgh, raising the stakes in an intensifying race to deploy autonomous vehicles. The ride-hailing company said Thursday that customers will be able to opt into the test program, which will use autonomous Ford Fusions summoned through the touch of a smartphone. Although other companies are testing self-driving cars on public roads, this is the first time the public can get access to them. The rides, which come with a human backup driver to handle situations that the autonomous cars haven't seen, will be free to those willing to take part, the company said. Uber, which has a self-driving research lab in Pittsburgh, has no immediate plans to deploy autonomous cars beyond the Pittsburgh experiment.

You could say the job of the sports fan is not only to cheer but to jeer. American sprinter Justin Gatlin, who has been suspended in the past for doping, entered Olympic Stadium before his 100-meter race to resounding boos. Competitors are also a part of the ritual. After winning a gold medal, American swimmer Lilly King wagged her finger to mock her Russian competitor Yulia Efimova, who previously had been suspended for doping. To philosopher Julian Savulescu, the boos and censures ring with, if not outright hypocrisy, short memory spans. "Caffeine is a performance-enhancer," he says. "It used to be banned and now it's allowed." Savulescu, a native Australian, who directs the Uehiro Center for Practical Ethics at the University of Oxford, has been one of the loudest critics in recent years of doping policies. Sports governing bodies have had restrictions in place for decades, he says, and have had little effect. Athletes will always find a way to beat the system, he says, and like most sports fans, Savulescu laments that doping creates an uneven playing field. But unlike most fans, Savulescu thinks the solution is to make doping legal in sports.

It may not look like much, but this wiggly little micro-robot is surprisingly powerful and complex. Inspired by the rippling locomotion of caterpillars, physics researchers at the University of Warsaw created the robot that at first glance appears to be nothing more than a thin transparent strip. But its body is made from light sensitive elastomer aligned in a molecular pattern, the secret to its creepy-crawly movement. Exposure to light causes its body to contract in a wave-like ripple, propelling its body forward. By controlling the lighting conditions, the researchers were able to get the robot to perform different actions.

A six month old child's spatial awareness can reveal how well it will do at maths later in life, researchers have found. The groundbreaking study is the earliest link between spatial awareness and maths, and could explain why some people embrace maths, while others feel they are bad at it and avoid it. It shows spatial reasoning measured in infancy predicts how children do at maths at four years of age. Psychologist Stella Lourenco, whose lab conducted the research, with one of the participants. The Emory study found spatial reasoning measured at six months infancy predicts how children do at maths at four years of age.

High-Dimensional Mixed Graphical Models Jie Cheng †, Tianxi Li‡, Elizaveta Levina‡, Ji Zhu‡ † Google, Inc.,‡ Department of Statistics, University of Michigan March 22, 2018 Abstract While graphical models for continuous data (Gaussian graphical models) and discrete data (Ising models) have been extensively studied, there is little work on graphical models for data sets with both continuous and discrete variables (mixed data), which are common in many scientific applications. We propose a novel graphical model for mixed data, which is simple enough to be suitable for high-dimensional data, yet flexible enough to represent all possible graph structures. We develop a computationally efficient regression-based algorithm for fitting the model by focusing on the conditional log-likelihood of each variable given the rest. The parameters have a natural group structure, and sparsity in the fitted graph is attained by incorporating a group lasso penalty, approximated by a weighted lasso penalty for computational efficiency. We demonstrate the effectiveness of our method through an extensive simulation study and apply it to a music annotation data set (CAL500), obtaining a sparse and interpretable graphical model relating the continuous features of the audio signal to binary variables such as genre, emotions, and usage associated with particular songs. 1 arXiv:1304.2810v3 Key Words: Conditional Gaussian density, Graphical model, Group lasso, Mixed variables, Music annotation. 1 Introduction Graphical models have proven to be a useful tool in representing the conditional dependency structure of multivariate distributions. The undirected graphical model in particular, sometimes also referred to as the Markov network, has drawn a notable amount of attention over the past decade. In an undirected graphical model, nodes in the graph represent the variables, while an edge between a pair of variables indicates that they are dependent conditional on all other variables. The properties of these models are by now well understood and studied both in the classical and the high-dimensional settings. Both these models can only deal with variables of one kind - either all continuous variables in Gaussian models or all binary variables in the Ising model (extensions of the Ising model to general discrete data, while possible in principle, are rarely used in 2 practice). In many applications, however, data sources are complex and varied, and frequently result in mixed types of data, with both continuous and discrete variables present in the same dataset. In this paper, we will focus on graphical models for this type of mixed data (mixed graphical models).

In this paper we introduce a novel framework for making exact nonparametric Bayesian inference on latent functions, that is particularly suitable for Big Data tasks. Firstly, we introduce a class of stochastic processes we refer to as string Gaussian processes (string GPs), which are not to be mistaken for Gaussian processes operating on text. We construct string GPs so that their finite-dimensional marginals exhibit suitable local conditional independence structures, which allow for scalable, distributed, and flexible nonparametric Bayesian inference, without resorting to approximations, and while ensuring some mild global regularity constraints. Furthermore, string GP priors naturally cope with heterogeneous input data, and the gradient of the learned latent function is readily available for explanatory analysis. Secondly, we provide some theoretical results relating our approach to the standard GP paradigm. In particular, we prove that some string GPs are Gaussian processes, which provides a complementary global perspective on our framework. Finally, we derive a scalable and distributed MCMC scheme for supervised learning tasks under string GP priors. The proposed MCMC scheme has computational time complexity $\mathcal{O}(N)$ and memory requirement $\mathcal{O}(dN)$, where $N$ is the data size and $d$ the dimension of the input space. We illustrate the efficacy of the proposed approach on several synthetic and real-world datasets, including a dataset with $6$ millions input points and $8$ attributes.

We consider the problem of solving mixed random linear equations with $k$ components. This is the noiseless setting of mixed linear regression. The goal is to estimate multiple linear models from mixed samples in the case where the labels (which sample corresponds to which model) are not observed. We give a tractable algorithm for the mixed linear equation problem, and show that under some technical conditions, our algorithm is guaranteed to solve the problem exactly with sample complexity linear in the dimension, and polynomial in $k$, the number of components. Previous approaches have required either exponential dependence on $k$, or super-linear dependence on the dimension. The proposed algorithm is a combination of tensor decomposition and alternating minimization. Our analysis involves proving that the initialization provided by the tensor method allows alternating minimization, which is equivalent to EM in our setting, to converge to the global optimum at a linear rate.

Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem. Among the existing methods, Low-Rank Representation (LRR) based method is quite superior in terms of its effectiveness, intuitiveness and robustness to noise corruptions. However, it aggressively tries to learn a common low-dimensional subspace for multi-view data, while inattentively ignoring the local manifold structure in each view, which is critically important to the spectral clustering; worse still, the low-rank minimization is enforced to achieve the data correlation consensus among all views, failing to flexibly preserve the local manifold structure for each view. In this paper, 1) we propose a multi-graph laplacian regularized LRR with each graph laplacian corresponding to one view to characterize its local manifold structure. 2) Instead of directly enforcing the low-rank minimization among all views for correlation consensus, we separately impose low-rank constraint on each view, coupled with a mutual structural consensus constraint, where it is able to not only well preserve the local manifold structure but also serve as a constraint for that from other views, which iteratively makes the views more agreeable. Extensive experiments on real-world multi-view data sets demonstrate its superiority.

This paper addresses network anomography, that is, the problem of inferring network-level anomalies from indirect link measurements. This problem is cast as a low-rank subspace tracking problem for normal flows under incomplete observations, and an outlier detection problem for abnormal flows. Since traffic data is large-scale time-structured data accompanied with noise and outliers under partial observations, an efficient modeling method is essential. To this end, this paper proposes an online subspace tracking of a Hankelized time-structured traffic tensor for normal flows based on the Candecomp/PARAFAC decomposition exploiting the recursive least squares (RLS) algorithm. We estimate abnormal flows as outlier sparse flows via sparsity maximization in the underlying under-constrained linear-inverse problem. A major advantage is that our algorithm estimates normal flows by low-dimensional matrices with time-directional features as well as the spatial correlation of multiple links without using the past observed measurements and the past model parameters. Extensive numerical evaluations show that the proposed algorithm achieves faster convergence per iteration of model approximation, and better volume anomaly detection performance compared to state-of-the-art algorithms.