With online payment platforms being ubiquitous and important, fraud transaction detection has become the key for such platforms, to ensure user account safety and platform security. In this work, we present a novel method for detecting fraud transactions by leveraging patterns from both users' static profiles and users' dynamic behaviors in a unified framework. To address and explore the information of users' behaviors in continuous time spaces, we propose to use \emph{time attention based recurrent layers} to embed the detailed information of the time interval, such as the durations of specific actions, time differences between different actions and sequential behavior patterns,etc., in the same latent space. We further combine the learned embeddings and users' static profiles altogether in a unified framework. Extensive experiments validate the effectiveness of our proposed methods over state-of-the-art methods on various evaluation metrics, especially on \emph{recall at top percent} which is an important metric for measuring the balance between service experiences and risk of potential losses.

Behaviour prediction function of an autonomous vehicle predicts the future states of the nearby vehicles based on the current and past observations of the surrounding environment. This helps enhance their awareness of the imminent hazards. However, conventional behaviour prediction solutions are applicable in simple driving scenarios that require short prediction horizons. Most recently, deep learning-based approaches have become popular due to their superior performance in more complex environments compared to the conventional approaches. Motivated by this increased popularity, we provide a comprehensive review of the state-of-the-art of deep learning-based approaches for vehicle behaviour prediction in this paper. We firstly give an overview of the generic problem of vehicle behaviour prediction and discuss its challenges, followed by classification and review of the most recent deep learning-based solutions based on three criteria: input representation, output type, and prediction method. The paper also discusses the performance of several well-known solutions, identifies the research gaps in the literature and outlines potential new research directions.

Sudheesh Nair, CEO of ThoughtSpot earnestly campaigns for artificial intelligence as a panacea for restoring our humanity - by making us able to do more work. Whether AI is helping a commuter navigate through a city or supporting a doctor's medical diagnosis, it relieves humans from mind-numbing, repetitive and error-prone tasks. This scares some business leaders, who worry AI could make people lazy, feckless and over-dependent. The more utopian minded - me included - see AI improving society and business while individuals get to enjoy happier, more fulfilling lives. Fortunately, this need not launch yet another polarised debate.

British Airways is set to trial artificial intelligence powered robots at Heathrow Terminal 5. In an announcement Thursday, the airline said the autonomous robots had been programmed to "interact with passengers" in multiple languages and would be able to answer "thousands" of questions, providing passengers with services such as real-time flight information. The robots are being provided by a technology company called BotsAndUs and the trial will start in 2020. British Airways added that the robots would also have the capacity to escort passengers to locations such as special assistance zones. "These smart robots are the latest innovation allowing us to free up our people to deal with immediate issues and offer that one-on-one service we know our customers appreciate," Ricardo Vidal, who is head of innovation at British Airways, said in a statement.

Community detection is considered as a fundamental task in analyzing social networks. Even though many techniques have been proposed for community detection, most of them are based exclusively on the connectivity structures. However, there are node features in real networks, such as gender types in social networks, feeding behavior in ecological networks, and location on e-trading networks, that can be further leveraged with the network structure to attain more accurate community detection methods. We propose a novel probabilistic graphical model to detect communities by taking into account both network structure and nodes' features. The proposed approach learns the relevant features of communities through a generative probabilistic model without any prior assumption on the communities. Furthermore, the model is capable of determining the strength of node features and structural elements of the networks on shaping the communities. The effectiveness of the proposed approach over the state-of-the-art algorithms is revealed on synthetic and benchmark networks.

On 7 November 2019, the Australian Federal Government's Minister for Industry, Innovation, and Science, Karen Andrews, announced the Australian …

Ride-hailing major Ola on Monday announced to expand its Artificial Intelligence (AI)-based safety feature called'Guardian' across several cities in the country. 'Guardian' uses real-time data from rides to automatically detect irregular trip activity, including prolonged stops and unexpected route deviations. After running a pilot project, the feature is now live in 16 Indian cities as well as in Perth, Australia and Ola aims to take'Guardian' to more cities in the coming quarter. "We are focused on developing innovations that place customer safety at the heart of platform experience. Guardian brings together the precision of artificial intelligence with the assurance of human intervention, enabling a uniform and safe mobility experience across the markets we operate in," Arun Srinivas, Chief Sales and Marketing Officer, Ola, said in a statement.

Abstract--Space-time adaptive processing (ST AP) algorithms with coprime arrays can provide good clutter suppression po - tential with low cost in airborne radar systems as compared with their uniform linear arrays counterparts. However, th e performance of these algorithms is limited by the training samples support in practical applications. T o address this issue, a robust two-stage reduced-dimension (RD) sparsity-aware S T AP algorithm is proposed in this work. In the first stage, an RD virtual snapshot is constructed using all spatial channels but only m adjacent Doppler channels around the target Doppler frequency to reduce the slow-time dimension of the signal. In the second stage, an RD sparse measurement modeling is formulated based on the constructed RD virtual snapshot, wh ere the sparsity of clutter and the prior knowledge of the clutte r ridge are exploited to formulate an RD overcomplete diction ary. Moreover, an orthogonal matching pursuit (OMP)-like metho d is proposed to recover the clutter subspace. In order to set the stopping parameter of the OMP-like method, a robust clutter rank estimation approach is developed. Compared wi th recently developed sparsity-aware ST AP algorithms, the si ze of the proposed sparse representation dictionary is much smal ler, resulting in low complexity. Simulation results show that t he proposed algorithm is robust to prior knowledge errors and can provide good clutter suppression performance in low sam ple support. Index T erms--Robust space-time adaptive processing, coprime arrays, prior knowledge, reduced-dimension, sparsity-aw are.

Signalized intersections are managed by controllers that assign right of way (green, yellow, and red lights) to non-conflicting directions. Optimizing the actuation policy of such controllers is expected to alleviate traffic congestion and its adverse impact. Given such a safety-critical domain, the affiliated actuation policy is required to be interpretable in a way that can be understood and regulated by a human. This paper presents and analyzes several on-line optimization techniques for tuning interpretable control functions. Although these techniques are defined in a general way, this paper assumes a specific class of interpretable control functions (polynomial functions) for analysis purposes. We show that such an interpretable policy function can be as effective as a deep neural network for approximating an optimized signal actuation policy. We present empirical evidence that supports the use of value-based reinforcement learning for on-line training of the control function. Specifically, we present and study three variants of the Deep Q-learning algorithm that allow the training of an interpretable policy function. Our Deep Regulatable Hardmax Q-learning variant is shown to be particularly effective in optimizing our interpretable actuation policy, resulting in up to 19.4% reduced vehicles delay compared to commonly deployed actuated signal controllers.

Automatic differentiation frameworks are optimized for exactly one thing: computing the average mini-batch gradient. Y et, other quantities such as the variance of the mini-batch gradients or many approximations to the Hessian can, in theory, be computed efficiently, and at the same time as the gradient. While these quantities are of great interest to researchers and practitioners, current deep-learning software does not support their automatic calculation. Manually implementing them is burdensome, inefficient if done na ıvely, and the resulting code is rarely shared. This hampers progress in deep learning, and unnecessarily narrows research to focus on gradient descent and its variants; it also complicates replication studies and comparisons between newly developed methods that require those quantities, to the point of impossibility. Its capabilities are illustrated by benchmark reports for computing additional quantities on deep neural networks, and an example application by testing several recent curvature approximations for optimization. The success of deep learning and the applications it fuels can be traced to the popularization of automatic differentiation frameworks. However, this specialization also has its shortcomings: it assumes the user only wants to compute gradients or, more precisely, the average of gradients across a mini-batch of examples. Other quantities can also be computed with automatic differentiation at a comparable cost or minimal overhead to the gradient backpropagation pass; for example, approximate second-order information or the variance of gradients within the batch. These quantities are valuable to understand the geometry of deep neural networks, for the identification of free parameters, and to push the development of more efficient optimization algorithms. But researchers who want to investigate their use face a chicken-and-egg problem: automatic differentiation tools required to go beyond standard gradient methods are not available, but there is no incentive for their implementation in existing deep-learning software as long as no large portion of the users need it. Second-order methods for deep learning have been continuously investigated for decades (e.g., Becker & Le Cun, 1989; Amari, 1998; Bordes et al., 2009; Martens & Grosse, 2015).