When you move to another country as an adult, the language flows around you like a river. Perhaps a child can immediately abandon himself to the current, but most older people will begin by picking out the words and phrases that seem to matter most, which is what I did after my family moved to Cairo, in October of 2011. It was the first fall after the Arab Spring; Hosni Mubarak, the former President, had been forced to resign the previous February. Every weekday, my wife, Leslie, and I met with a tutor for two hours at a language school called Kalimat, where we studied Egyptian Arabic. At the end of each session, we made a vocabulary list. In early December, following the first round of the nation's parliamentary elections, which had been dominated by the Muslim Brotherhood, my language notebook read: On many days, I went to Tahrir Square, to report on the ongoing revolution. If I heard unfamiliar words or phrases, I brought them back to class. The following month, I learned "tear gas," "slaughter," and "Can you speak more slowly?" "Conspiracy theory" appeared in my notebook on the same day as "fried potatoes." Sometimes I wondered about the strangeness of Tahrir-speak, and what my Arabic would have been like if I had arrived ten years earlier. But it would have been different at any time, in any place: you can never step into the same language twice. Even eternal phrases took on a new texture in the light of the revolution. After I could understand some of the radio talk shows that cabbies played, I realized that callers and hosts exchanged Islamic greetings for a full half minute before settling down to heated arguments about the new regime. Our textbook was entitled "Dardasha"--"Chatter"--and it outlined set conversations that I soon carried out with neighbors, using phrases that would never be touched by Tahrir: "May peace, mercy, and the blessings of God be upon you." One of our teachers, Rifaat Amin, prepared a five-page handout entitled "Arabic Expressions of Social Etiquette." This supplemented "Dardasha," which also featured some lessons about social traditions, including the evil eye, the belief that envy can cause misfortune. In "Dardasha," icons of little bombs with burning fuses had been printed next to the kind of phrase that, even during a revolution, qualified as explosive: "Your son is really smart, Madame Fathiya."

Label assignment problems with large state spaces are important tasks especially in computer vision. Often the pairwise interaction (or smoothness prior) between labels assigned at adjacent nodes (or pixels) can be described as a function of the label difference. Exact inference in such labeling tasks is still difficult, and therefore approximate inference methods based on a linear programming (LP) relaxation are commonly used in practice. In this work we study how compact linear programs can be constructed for general piecwise linear smoothness priors. The number of unknowns is O(LK) per pairwise clique in terms of the state space size $L$ and the number of linear segments K. This compares to an O(L^2) size complexity of the standard LP relaxation if the piecewise linear structure is ignored. Our compact construction and the standard LP relaxation are equivalent and lead to the same (approximate) label assignment.

We study a spectral initialization method that serves a key role in recent work on estimating signals in nonconvex settings. Previous analysis of this method focuses on the phase retrieval problem and provides only performance bounds. In this paper, we consider arbitrary generalized linear sensing models and present a precise asymptotic characterization of the performance of the method in the high-dimensional limit. Our analysis also reveals a phase transition phenomenon that depends on the ratio between the number of samples and the signal dimension. When the ratio is below a minimum threshold, the estimates given by the spectral method are no better than random guesses drawn from a uniform distribution on the hypersphere, thus carrying no information; above a maximum threshold, the estimates become increasingly aligned with the target signal. The computational complexity of the method, as measured by the spectral gap, is also markedly different in the two phases. Worked examples and numerical results are provided to illustrate and verify the analytical predictions. In particular, simulations show that our asymptotic formulas provide accurate predictions for the actual performance of the spectral method even at moderate signal dimensions.

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch. H-Nets use a rich, parameter-efficient and low computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.

We introduce a novel approach for estimating Latent Dirichlet Allocation (LDA) parameters from collapsed Gibbs samples (CGS), by leveraging the full conditional distributions over the latent variable assignments to efficiently average over multiple samples, for little more computational cost than drawing a single additional collapsed Gibbs sample. Our approach can be understood as adapting the soft clustering methodology of Collapsed Variational Bayes (CVB0) to CGS parameter estimation, in order to get the best of both techniques. Our estimators can straightforwardly be applied to the output of any existing implementation of CGS, including modern accelerated variants. We perform extensive empirical comparisons of our estimators with those of standard collapsed inference algorithms on real-world data for both unsupervised LDA and Prior-LDA, a supervised variant of LDA for multi-label classification. Our results show a consistent advantage of our approach over traditional CGS under all experimental conditions, and over CVB0 inference in the majority of conditions. More broadly, our results highlight the importance of averaging over multiple samples in LDA parameter estimation, and the use of efficient computational techniques to do so.

TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for speaker comparison purposes. Experiments on short (between 500ms and 5s) speech turn comparison and speaker change detection show that TristouNet brings significant improvements over the current state-of-the-art techniques for both tasks.

As the hundreds of people who have publicly posted pictures of their debit cards on Twitter can attest, it's often easy to unwittingly expose private information in the age of social media. But what if a friendly automated assistant, similar to Siri or Alexa, warned you before you share sensitive images, potentially mitigating threats like online stalking and identity theft? That's the idea behind a recent study from researchers at the Max Planck Institute for Informatics in Germany, who say they've built an AI-powered privacy watchdog that can learn a person's privacy preferences and caution them whenever private information might be exposed in the pictures they post to social media. "Our model is trained to predict the user specific privacy risk and even outperforms the judgment of the users, who often fail to follow their own privacy preferences," the researchers write in a recent paper, which awaits peer review. "In fact -- as our study shows -- people frequently misjudge the privacy relevant information content in an image -- which leads to failure of enforcing their own privacy preferences."

Artificial Intelligence and Machine Learning is revolutionizing the healthcare industry. Here's what you need to know. Machine Learning is a growing and diverse field of Artificial Intelligence which studies algorithms that are capable of automatically learning from data and making predictions based on data. Machine learning is one of the most exciting technological areas of study today. Each week there are new advancements, new technologies, new applications, and new opportunities.

The evidence that Russia hacked the US to influence the outcome of the 2016 presidential election continues to grow. The latest comes from AFP, which says that that a Russian "computer expert" was arrested in Spain today at the Barcelona airport on suspicions of hacking the US presidential election campaigns. Furthermore, the US has already put in an extradition request so that the subject Piotr Levashov would have to stand trial here for his alleged crimes. The US has 40 days to present its extradition request to Spain; given that Levashov's arrest reportedly was the result of an "international complaint," it's reasonable to guess that the US is the one who asked the arrest to be made. Indeed, Piotr Levashov's wife Maria told Russian TV that her husband was detained at the request of American authorities.

More than a quarter of a million people might be caught up in one of the most damaging hacks in recent history. The lender has confirmed that it was the victim of a huge attack that could have leaked the personal details of up to 270,000 customers, almost all of whom were in the UK. That number includes former customers who details may also have been stolen. The payday loan company, which has been repeatedly criticised for preying on vulnerable people with extremely high interest loans, said that it was aware of something amiss last week but didn't realise until Friday that people's information was available. The I.F.O. is fuelled by eight electric engines, which is able to push the flying object to an estimated top speed of about 120mph.