More than two years after a multi-sided civil war erupted inside Yemen that allowed Al Qaeda's local franchise to amass power and seize territory, President Trump has directed the Pentagon to embark on a complicated counter-terrorism campaign. Trump's decision, just six weeks into his presidency, intends to reverse the largely unchecked expansion across southern Yemen of the group, Al Qaeda in the Arabian Peninsula. The willingness to expand counter-terrorism operations inside war-torn Yemen was the latest signal that Trump is more willing to defer to military commanders on national security policy than President Obama, who was criticized publicly by three of his four Defense secretaries and privately by uniformed officers for micromanaging the military. Over two days this week, armed drones and warplanes conducted more than 30 airstrikes against suspected Al Qaeda positions in three Yemeni provinces, marking the first U.S. attacks in the country since an ill-fated Navy SEAL raid in January that killed two dozen civilians, including women and children, Al Qaeda militants and Chief Petty Officer William "Ryan" Owens. The aerial bombardment is expected to continue into the coming week.

Worries that robots may end up replacing human workers have lately sparked debates over the role of artificial intelligence in corporate jobs. During a Fortune conference that tackled the subject and its various implications, voices from IBM and Google proceeded to dissipate concerns and state there's no need for alarm. Present at the Most Powerful Women International Summit in Hong Kong on March 2, women leaders of the two tech companies reassured the public that there's no need to worry about an A.I. takeover, as the technology is here to help and could significantly improve the activity of firms. According to Vanitha Narayanan, chairman of IBM India, the first corporate sector to gain the most from this technology would be that of service-oriented companies. Just like what her boss, IBM CEO Ginni Rometty, previously explained at the World Economic Forum, Narayanan reaffirmed the idea of a partnership between humans and machine.

Artificial intelligence has made some great developments toward speeding up cancer diagnosis so far in 2017. Last month it was announced that AI from Sophia Genetics was helping to accelerate patient diagnosis across Latin America. Earlier this year researchers at Stanford University developed a deep learning algorithm that can analyse skin cancer as accurately as a human doctor. Now, Israel-based company, Medical EarlySign has announced the ability of its AI tool to identify the top 1% at highest risk of undiagnosed colorectal cancer (CRC). The machine learning developer announced the first-year results of its implementation with Maccabi Healthcare Services (MHS), for ColonFlag, a tool developed in collaboration with MHS to identify individuals with a high probability of having CRC.

Naver and LINE Corp. unveiled their artificial intelligence (AI)-based assistant platform Clova at the Mobile World Congress (MWC) 2017 in Barcelona, the companies reported Thursday. According to Naver and its mobile service subsidiary, Clova, which stands for "cloud virtual assistant," aims at an AI platform that works based on the five human senses. "Clova is a platform that incorporates various AI technologies including vocal, visual and conversational engines," LINE Corp. CEO Idezawa Takeshi said in his keynote at the MWC 2017, Wednesday. The two companies are jointly developing Clova by improving Naver Labs' voice-recognizing assistant service AMICA. They said it will expand the system to have more cognitive capabilities to make it more humanlike.

Taking a look back at seven days of news and headlines across the world of Android, this week's Android Circuit includes Samsung's efforts to spoil MWC, new images leaked of the Galaxy S8, asking if the new Nokia handsets are worthy of the Nokia name, a hands-on review of the Nokia 5, the LG G6 design, Huawei's new camera technology, the return of the BlackBerry keyboard, and the designer of the Psion PDA returning with an Android dream machine. Android Circuit is here to remind you of a few of the many things that have happened around Android in the last week (and you can find the weekly Apple news digest here). Although it had previously declared that it would not be announced the Galaxy S8 at this week's Mobile World Congress in Barcelona, the South Korean company announced when it would be announcing its new flagship. It looks like a tactical move to remind consumers not to fall in love with the new devices from MWC until it can consider Samsung's latest: But today's news about the Galaxy S8 launch wasn't about reassuring the public. It was about taking away some of the momentum that the S8's rivals could gain from Mobile World Congress.

It's been a rocky week, at home and abroad. Bomb threats were made against Jewish community centers and schools. More controversy over Russia's role in the 2016 elections engulfed Congress and the White House. Russia and China vetoed new sanctions on Syria. Deadly tornadoes ripped across the Midwest.

Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution. There are many variants of Poisson factorization methods who show state-of-the-art performance on real-world recommendation tasks. However, most of them do not explicitly take into account the temporal behavior and the recurrent activities of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model and brings to the table a rich family of time-sensitive factorization models. To elaborate, we instantiate several variants of RPF who are capable of handling dynamic user preferences and item specification (DRPF), modeling the social-aspect of product adoption (SRPF), and capturing the consumption heterogeneity among users and items (HRPF). We also develop a variational algorithm for approximate posterior inference that scales up to massive data sets. Furthermore, we demonstrate RPF's superior performance over many state-of-the-art methods on synthetic dataset, and large scale real-world datasets on music streaming logs, and user-item interactions in M-Commerce platforms.

Topic models are one of the most popular methods for learning representations of text, but a major challenge is that any change to the topic model requires mathematically deriving a new inference algorithm. A promising approach to address this problem is autoencoding variational Bayes (AEVB), but it has proven diffi- cult to apply to topic models in practice. We present what is to our knowledge the first effective AEVB based inference method for latent Dirichlet allocation (LDA), which we call Autoencoded Variational Inference For Topic Model (AVITM). This model tackles the problems caused for AEVB by the Dirichlet prior and by component collapsing. We find that AVITM matches traditional methods in accuracy with much better inference time. Indeed, because of the inference network, we find that it is unnecessary to pay the computational cost of running variational optimization on test data. Because AVITM is black box, it is readily applied to new topic models. As a dramatic illustration of this, we present a new topic model called ProdLDA, that replaces the mixture model in LDA with a product of experts. By changing only one line of code from LDA, we find that ProdLDA yields much more interpretable topics, even if LDA is trained via collapsed Gibbs sampling.

Early and accurate identification of parkinsonian syndromes (PS) involving presynaptic degeneration from non-degenerative variants such as Scans Without Evidence of Dopaminergic Deficit (SWEDD) and tremor disorders, is important for effective patient management as the course, therapy and prognosis differ substantially between the two groups. In this study, we use Single Photon Emission Computed Tomography (SPECT) images from healthy normal, early PD and SWEDD subjects, as obtained from the Parkinson's Progression Markers Initiative (PPMI) database, and process them to compute shape- and surface fitting-based features for the three groups. We use these features to develop and compare various classification models that can discriminate between scans showing dopaminergic deficit, as in PD, from scans without the deficit, as in healthy normal or SWEDD. Along with it, we also compare these features with Striatal Binding Ratio (SBR)-based features, which are well-established and clinically used, by computing a feature importance score using Random forests technique. We observe that the Support Vector Machine (SVM) classifier gave the best performance with an accuracy of 97.29%. These features also showed higher importance than the SBR-based features. We infer from the study that shape analysis and surface fitting are useful and promising methods for extracting discriminatory features that can be used to develop diagnostic models that might have the potential to help clinicians in the diagnostic process.

Hey, game developers: William Gibson called. He wants his dystopian sci-fi future back. Walking among the flashy, flickering and noisy booths of the GDC show floor and its surrounding events, the pattern becomes clear -- a significant portion of these games have a strong sci-fi vibe, many of them dealing with the idea of futuristic corporate overreach and gritty technological espionage. Take the ID@Xbox showcase for example. Of the 20 games on display, at least half are set in sci-fi worlds or feature dystopian themes (or both), including Tacoma, Tokyo 42, Tower 57, Songbringer and Aven Colony.