SHANGHAI (Reuters) - China's capital city has given the green light to tech giant Baidu Inc to test self-driving cars on city streets, an important step as the country looks to bolster its position in the global race for autonomous vehicles.

Have you noticed that more and more websites now seem to have someone just waiting there to answer your questions? It's a familiar chat interface with the first line saying "Hi There, I'm Amy. Let me know if I can answer any questions" and there's a text box you can type a response into. As soon as you engaged with the form, then a human took over and chatted with you. Going forward though, any interactions you have in which you type text to speak to a company will be through the use of a chatbot built by one of the many chatbot startups popping up all over the place.

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, and generalization before moving on to more advanced topics in both supervised and unsupervised learning. Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines), and variational methods. Throughout, we emphasize the many natural connections between ML and statistical physics. A notable aspect of the review is the use of Python notebooks to introduce modern ML/statistical packages to readers using physics-inspired datasets (the Ising Model and Monte-Carlo simulations of supersymmetric decays of proton-proton collisions). We conclude with an extended outlook discussing possible uses of machine learning for furthering our understanding of the physical world as well as open problems in ML where physicists maybe able to contribute. (Notebooks are available at https://physics.bu.edu/~pankajm/MLnotebooks.html )

In this paper, we investigate the capability of the universal Kriging (UK) model for single-objective global optimization applied within an efficient global optimization (EGO) framework. We implemented this combined UK-EGO framework and studied four variants of the UK methods, that is, a UK with a first-order polynomial, a UK with a second-order polynomial, a blind Kriging (BK) implementation from the ooDACE toolbox, and a polynomial-chaos Kriging (PCK) implementation. The UK-EGO framework with automatic trend function selection derived from the BK and PCK models works by building a UK surrogate model and then performing optimizations via expected improvement criteria on the Kriging model with the lowest leave-one-out cross-validation error. Next, we studied and compared the UK-EGO variants and standard EGO using five synthetic test functions and one aerodynamic problem. Our results show that the proper choice for the trend function through automatic feature selection can improve the optimization performance of UK-EGO relative to EGO. From our results, we found that PCK-EGO was the best variant, as it had more robust performance as compared to the rest of the UK-EGO schemes; however, total-order expansion should be used to generate the candidate trend function set for high-dimensional problems. Note that, for some test functions, the UK with predetermined polynomial trend functions performed better than that of BK and PCK, indicating that the use of automatic trend function selection does not always lead to the best quality solutions. We also found that although some variants of UK are not as globally accurate as the ordinary Kriging (OK), they can still identify better-optimized solutions due to the addition of the trend function, which helps the optimizer locate the global optimum.

This paper proposes Architectural Pattern Recommender (APR) system which helps in such architecture selection process. Main contribution of this work is in replacing the manual effort required to identify and analyse relevant architectural patterns in context of a particular set of software requirements. Key input to APR is a set of architecturally significant use cases concerning the application being developed. Central idea of APR's design is two folds: a) transform the unstructured information about software architecture design into a structured form which is suitable for recognizing textual entailment between a requirement scenario and a potential architectural pattern. b) leverage the rich experiential knowledge embedded in discussions on professional developer support forums such as Stackoverflow to check the sentiment about a design decision. APR makes use of both the above elements to identify a suitable architectural pattern and assess its suitability for a given set of requirements. Efficacy of APR has been evaluated by comparing its recommendations for "ground truth" scenarios (comprising of applications whose architecture is well known).

For a learning task, data can usually be collected from different sources or be represented from multiple views. For example, laboratory results from different medical examinations are available for disease diagnosis, and each of them can only reflect the health state of a person from a particular aspect/view. Therefore, different views provide complementary information for learning tasks. An effective integration of the multi-view information is expected to facilitate the learning performance. In this paper, we propose a general predictor, named multi-view machines (MVMs), that can effectively include all the possible interactions between features from multiple views. A joint factorization is embedded for the full-order interaction parameters which allows parameter estimation under sparsity. Moreover, MVMs can work in conjunction with different loss functions for a variety of machine learning tasks. A stochastic gradient descent method is presented to learn the MVM model. We further illustrate the advantages of MVMs through comparison with other methods for multi-view classification, including support vector machines (SVMs), support tensor machines (STMs) and factorization machines (FMs).

In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make decisions by identifying significant pixels for prediction. A model shows wrong classification output always learns wrong features and shows wrong saliency as well. Our approach shows good performance on detecting adversarial perturbations. We quantitatively evaluate generalization ability of the detector, showing that detectors trained with strong adversaries perform well on weak adversaries.

Right now our smartphone notifications are pretty "dumb" in the sense that as soon as something pops up, we are notified straight away, whether it be an email, message, a tag/mention on Facebook, a sales event, and so on. The onus is mostly on the user to manage their notifications and to choose what they want or don't want to see. However what if our phones could become smart enough to know what we usually respond to? That's something that two developers over in Taiwan are trying to do, where through the use of machine learning, our phones could start to learn our habits to determine what notifications it should display and which shouldn't. The developers, TonTon Hsien-de Huang and Hung-Yu Kao have dubbed this'Clicksequence-aware deeP neural network (DNN)-based Pop-uPs recOmmendation' or C-3PO, which like we said is an algorithm that learns what users respond to and which they don't.

Ubisoft is participating in the Women in Gaming Rally at GDC this week. It's one of the first things the 20 or so journalists pooled between the open bar and the canapes on the second floor of Hotel Zetta were told -- mentioned right after the evening's embargo information and just before spokespeople split the reporters into three groups and shepherded them to their appropriate meetings. There were three sessions, each 20 minutes long and covering distinct topics: Online ecosystems, artificial intelligence, and new studio openings. After each session, the groups would rotate to see the next presentation, for an hour total of on-the-record, Ubisoft-centric back-patting and glad-handing. But before any of that, Ubisoft representatives wanted reporters to know the studio would participate in the Women in Gaming Rally at GDC. This was the one hosted by Microsoft and held at the Jewish Contemporary Museum on Tuesday, not to be confused with the Women in Games International networking event sponsored by PlayStation and held at the headquarters of a local non-profit, also on Tuesday.

Entrepreneur First (EF), the company builder and "talent first" investor, held its ninth London Demo Day this afternoon. Once again, the pitches took place in front of a packed crowd at King's Place in London's King Cross area, seeing 19 startups pitch their wares to investors, press and other actors in the European tech scene. EF stands out from the plethora of demo days that the U.K. capital city hosts because of the way the investor backs individuals "pre-team, pre-idea" -- meaning that the companies pitching only came into existence over the last 6 months and perhaps may never have done so without the founders entering the programme. As is now a tradition, prior to the pitches, EF co-founder Matt Clifford took the chance to announce some EF news of its own. Already operating in London, Singapore and Berlin, the company builder -- which last year picked up backing in a $12.4 million round led by Silicon Valley's Greylock Partners -- is expanding to Hong Kong to double down on its Asia ambitions, kicking off with a local programme in July.