When you post a photo on Facebook, and the platform automatically tags the people in the image, you might not give much thought to the technology behind the convenience. However, when you discover that facial recognition technology could track you without your permission while you walk down a street in London, it might make you question the invasion of your privacy. Just like with any other new technology, facial recognition brings positives and negatives with it. Since it's here to stay and expanding, it's good to be aware of the pros and cons of facial recognition. What is facial recognition, and how does it work? Facial recognition is a biometric technology that uses distinguishable facial features to identify a person.

Nvidia and VMware on Monday announced a new software product that lets customers virtualize GPUs, either on premise or as part of VMware Cloud on AWS. The companies say it's the first hybrid cloud offering that lets enterprises use GPUs to accelerate AI, machine learning or deep learning workloads. "In a modern data center, organizations are going to be using GPUs to power AI, deep learning, analytics," John Fanelli, VP of product management for Nvidia, told reporters. "And due to the scale of those types of workloads, they're going to be doing some processing on premise in data centers, some processing in clouds and continually iterating between them." The new offering starts with the enterprise data center product -- Nvidia's new Virtual Compute Server (vComputeServer) software.

A former Google engineer was charged Tuesday with stealing closely guarded secrets that he later sold to Uber as the ride-hailing service scrambled to catch up in the high-stakes race to build robotic vehicles. The indictment filed by the U.S. Attorney's office in San Jose, California, is an offshoot of a lawsuit filed in 2017 by Waymo, a self-driving car pioneer spun off from Google. Uber agreed to pay Waymo $245 million to settle the case, but the federal judge overseeing the lawsuit made an unusual recommendation to open a criminal probe. Uber considered having self-driving technology crucial to survive. Anthony Levandowski, a pioneer in robotic vehicles, was charged with 33 counts of trade secrets theft.

Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and optimal control. By viewing deep neural networks as discrete-time nonlinear dynamical systems, we can analyze how information propagates through layers using mean field theory. When optimization algorithms are further recast as controllers, the ultimate goal of training processes can be formulated as an optimal control problem. In addition, we can reveal convergence and generalization properties by studying the stochastic dynamics of optimization algorithms. This viewpoint features a wide range of theoretical study from information bottleneck to statistical physics. It also provides a principled way for hyper-parameter tuning when optimal control theory is introduced. Our framework fits nicely with supervised learning and can be extended to other learning problems, such as Bayesian learning, adversarial training, and specific forms of meta learning, without efforts. The review aims to shed lights on the importance of dynamics and optimal control when developing deep learning theory.

There is a growing need for vehicle positioning information to support Advanced Driver Assistance Systems (ADAS), Connectivity (V2X), and Automated Driving (AD) features. These range from a need for road determination (<5 meters), lane determination (<1.5 meters), and determining where the vehicle is within the lane (<0.3 meters). This work examines the performance of Global Navigation Satellite Systems (GNSS) on 30,000 km of North American highways to better understand the automotive positioning needs it meets today and what might be possible in the near future with wide area GNSS correction services and multi-frequency receivers. This includes data from a representative automotive production GNSS used primarily for turn-by-turn navigation as well as an Inertial Navigation System which couples two survey grade GNSS receivers with a tactical grade Inertial Measurement Unit (IMU) to act as ground truth. The latter utilized networked Real-Time Kinematic (RTK) GNSS corrections delivered over a cellular modem in real-time. We assess on-road GNSS accuracy, availability, and continuity. Availability and continuity are broken down in terms of satellite visibility, satellite geometry, position type (RTK fixed, RTK float, or standard positioning), and RTK correction latency over the network. Results show that current automotive solutions are best suited to meet road determination requirements at 98% availability but are less suitable for lane determination at 57%. Multi-frequency receivers with RTK corrections were found more capable with road determination at 99.5%, lane determination at 98%, and highway-level lane departure protection at 91%.

Recently, the development and implementation of phishing attacks require little technical skills and costs. This uprising has led to an ever-growing number of phishing attacks on the World Wide Web daily. Consequently, proactive techniques to fight phishing attacks have become extremely necessary. In this paper, we propose a deep learning model HTMLPhish based on the HTML analysis of a web page for accurate phishing attack detection. By using our proposed HTMLPhish, the experimental results on a dataset of over 300,000 web pages yielded 97.2% accuracy, which significantly outperforms the traditional machine learning methods such as Support Vector Machine, Random Forest and Logistics Regression. We also show the advantage of HTMLPhish in the aspect of the temporal stability and robustness by testing our proposed model on a dataset collected after two months when the model was trained. In addition, HTMLPhish is a completely language-independent and client-side strategy which can, therefore, conduct web page phishing detection regardless of the textual language.

--Incorporating deep neural networks in image com-pressive sensing (CS) receives intensive attentions recently. As deep network approaches learn the inverse mapping directly from the CS measurements, a number of models have to be trained, each of which corresponds to a sampling rate. This may potentially degrade the performance of image CS, especially when multiple sampling rates are assigned to different blocks within an image. In this paper, we develop a multi-channel deep network for block-based image CS with performance significantly exceeding the current state-of-the-art methods. The significant performance improvement of the model is attributed to block-based sampling rates allocation and model-level removal of blocking artifacts. Specifically, the image blocks with a variety of sampling rates can be reconstructed in a single model by exploiting inter-block correlation. At the same time, the initially reconstructed blocks are reassembled into a full image to remove blocking artifacts within the network by unrolling a hand-designed block-based CS algorithm. Experimental results demonstrate that the proposed method outperforms the state-of-the-art CS methods by a large margin in terms of objective metrics, PSNR, SSIM, and subjective visual quality. Compressive sensing (CS), an emerging sampling and reconstructing strategy, can recover original signal from dramatically fewer measurements with a sub-Nyquist sampling rate [1]. As CS has the potentials of significantly improving the sampling speed and sensor energy efficiency, it has been applied in many practical applications, including single pixel imaging [2], fast magnetic resonance imaging [3], high-speed video cameras [4] and image encryption [5]. To deal with high-dimensional natural images efficiently, block-based CS is proposed as a lightweight CS approach [6]-[8]. In such strategy, a scene under view is partitioned into some small blocks, which are then sampled and reconstructed independently. Meaningful information is usually not uniformly distributed in an image, so the block partition benefits more fair allocation of the sensing resources for the whole image [9]. This work was supported by the National Natural Science Foundation of China (no.

While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis. Such domains rely on relational representations to capture complex relationships between entities and their attributes. Thus, we consider the problem of learning neural networks for relational data. We distinguish ourselves from current approaches that rely on expert hand-coded rules by learning relational random-walk-based features to capture local structural interactions and the resulting network architecture. We further exploit parameter tying of the network weights of the resulting relational neural network, where instances of the same type share parameters. Our experimental results across several standard relational data sets demonstrate the effectiveness of the proposed approach over multiple neural net baselines as well as state-of-the-art statistical relational models.

One prominent approach for data collection has been to automatically generate pseudo-language paired with logical forms, and paraphrase the pseudo-language to natural language through crowdsourcing (Wang et al., 2015). However, this data collection procedure often leads to low performance on real data, due to a mismatch between the true distribution of examples and the distribution induced by the data collection procedure. In this paper, we thoroughly analyze two sources of mismatch in this process: the mismatch in logical form distribution and the mismatch in language distribution between the true and induced distributions. We quantify the effects of these mismatches, and propose a new data collection approach that mitigates them. Assuming access to unlabeled utterances from the true distribution, we combine crowdsourcing with a paraphrase model to detect correct logical forms for the unlabeled utterances. On two datasets, our method leads to 70.6 accuracy on average on the true distribution, compared to 51.3 in paraphrasing-based data collection. 1 Introduction Conversing with a virtual assistant in natural language is one of the most exciting current applications of semantic parsing, the task of mapping natural language utterances to executable logical forms (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang et al., 2011). Semantic parsing models rely on supervised training data that pairs natural language utterances with logical forms. Alas, such data does not occur naturally, especially in virtual assistants that are meant to support thousands of different applications and use-cases. Thus, efficient data collection is per-Figure 1: An overview of G RA NNO, a method for annotating unlabeled utterances with their logical forms.

Recently, hybrid metaheuristics have become a trend in operations research. A successful example combines the Greedy Randomized Adaptive Search Procedures (GRASP) and data mining techniques, where frequent patterns found in high-quality solutions can lead to an efficient exploration of the search space, along with a significant reduction of computational time. In this work, a GRASP-based state-of-the-art heuristic for the Minimum Latency Problem (MLP) is improved by means of data mining techniques for two MLP variants. Computational experiments showed that the approaches with data mining were able to match or improve the solution quality for a large number of instances, together with a substantial reduction of running time. In addition, 88 new cost values of solutions are introduced into the literature. To support our results, tests of statistical significance, impact of using mined patterns, equal time comparisons and time-to-target plots are provided.