AI can be used for the early detection of virus outbreaks that might result in a pandemic. AI detected the coronavirus long before the world's population really knew what it was. On December 31st, a Toronto-based startup called BlueDot identified the outbreak in Wuhan, several hours after the first cases were diagnosed by local authorities. The BlueDot team confirmed the info its system had relayed and informed their clients that very day, nearly a week before Chinese and international health organisations made official announcements. Thanks to the speed and scale of AI, BlueDot was able to get a head start over everyone else.

Many companies in the biometric, digital identity, and cybersecurity space have shared predictions for 2020 with Biometric Update, touching on many of the key themes of the past year, and reflecting the wealth of opportunity, as well as the anxieties at play in the industry. Those predictions most closely thematically related to biometrics and our top news stories are collected below. "The global market for mobile biometrics is forecast to grow at an impressive 31.14 percent CAGR, adding $28.45 billion per year in incremental growth between 2018 and 2023, despite the CAGR decelerating by 22 percent in the period," points out Robert Prigge, CEO of Jumio. "The growth forecasts in the latest set of market analyst reports that indicate widespread adoption of biometrics technology: 22 percent for mobile biometrics, 22 percent for 3D sensors, and 19 percent for healthcare biometrics Facial authentication is impacting the physical security market, cloud-based subscription services are becoming more popular for security, and the Pentagon is expected to remain a source of opportunity for companies offering advanced authentication technologies. Although we are still in the early stages of biometric-based identity proofing and authentication, its development will serve as a viable solution for the growing fraud epidemic."

Coupled Matrix Tensor Factorization (CMTF) facilitates the integration and analysis of multiple data sources and helps discover meaningful information. Nonnegative CMTF (N-CMTF) has been employed in many applications for identifying latent patterns, prediction, and recommendation. However, due to the added complexity with coupling between tensor and matrix data, existing N-CMTF algorithms exhibit poor computation efficiency. In this paper, a computationally efficient N-CMTF factorization algorithm is presented based on the column-wise element selection, preventing frequent gradient updates. Theoretical and empirical analyses show that the proposed N-CMTF factorization algorithm is not only more accurate but also more computationally efficient than existing algorithms in approximating the tensor as well as in identifying the underlying nature of factors.

With the advent of consumer-grade products for presenting an immersive virtual environment (VE), there is a growing interest in utilizing VEs for testing human navigation behavior. However, preparing a VE still requires a high level of technical expertise in computer graphics and virtual reality, posing a significant hurdle to embracing the emerging technology. To address this issue, this paper presents Delayed Feedback based Immersive Navigation Environment (DeFINE), a framework that allows for easy creation and administration of navigation tasks within customizable VEs via intuitive graphical user interfaces and simple settings files. Importantly, DeFINE has a built-in capability to provide performance feedback to participants during an experiment, a feature that is critically missing in other similar frameworks. To demonstrate the usability of DeFINE from both experimentalists' and participants' perspectives, a case study was conducted in which participants navigated to a hidden goal location with feedback that differentially weighted speed and accuracy of their responses. In addition, the participants evaluated DeFINE in terms of its ease of use, required workload, and proneness to induce cybersickness. Results showed that the participants' navigation performance was affected differently by the types of feedback they received, and they rated DeFINE highly in the evaluations, validating DeFINE's architecture for investigating human navigation in VEs. With its rich out-of-the-box functionality and great customizability due to open-source licensing, DeFINE makes VEs significantly more accessible to many researchers.

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical nature of the meta-learning setting presents several challenges that can render conventional batch normalization ineffective, giving rise to the need to rethink normalization in this setting. We evaluate a range of approaches to batch normalization for meta-learning scenarios, and develop a novel approach that we call TaskNorm. Experiments on fourteen datasets demonstrate that the choice of batch normalization has a dramatic effect on both classification accuracy and training time for both gradient based and gradient-free meta-learning approaches. Importantly, TaskNorm is found to consistently improve performance. Finally, we provide a set of best practices for normalization that will allow fair comparison of meta-learning algorithms.

Variational inference techniques based on inducing variables provide an elegant framework for scalable posterior estimation in Gaussian process (GP) models. Most previous works treat the locations of the inducing variables, i.e. the inducing inputs, as variational hyperparameters, and these are then optimized together with GP covariance hyper-parameters. While some approaches point to the benefits of a Bayesian treatment of GP hyper-parameters, this has been largely overlooked for the inducing inputs. In this work, we show that treating both inducing locations and GP hyper-parameters in a Bayesian way, by inferring their full posterior, further significantly improves performance. Based on stochastic gradient Hamiltonian Monte Carlo, we develop a fully Bayesian approach to scalable GP and deep GP models, and demonstrate its competitive performance through an extensive experimental campaign across several regression and classification problems.

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities.

The AI in Financial Services Summit is designed specifically for leaders in Artificial Intelligence who are helping to transform the financial services sector in Australia and New Zealand. Coming together over a 2-day period, AI in Finance will act as a platform for leaders to discuss some of the major transformation projects and advancements taking place in 2020 and beyond. The amount of collective knowledge amongst AI leaders is powerful. Our aim is to bring that knowledge under one roof - to share, learn, brainstorm and unpack the weird and wonderful thing that is AI in finance. Hear a variety of use-cases with key learnings, discuss key regulatory changes, benchmark against your peers, and help strengthen the AI community.

In this blog, Microsoft talks about ways to address the top challenges to AI adoption through empowering inclusion, expanding access to accessible and affordable technology, supporting faculty and staff with skills, training, and resources, and partnering on long-terms AI strategies. Artificial intelligence is transforming higher education, according to a new study released today by IDC and commissioned by Microsoft. The report details the expected opportunity with AI in higher education and the challenges institutions must overcome to realize results. The study covered 509 higher education institutions in the US, and found that nearly all respondents--99.4 Fifteen percent called AI a "game-changer," and 54 percent of higher education institutions in the US have started to experiment with AI, while 38 percent have adopted AI as a core part of their business strategy.

By the end of 2019, there were more than 400 mass shootings in the U.S. It is the highest number of mass killings in the recent history. Gun violence in the United States needs no introduction. U. S. officials have been trying for years to find a solution to this problem, but the number of casualties is still increasing. But what if you were able to stop a shooter before he even begin to shoot? One way to do that is through artificial intelligence.