Due to the popularity of the Internet and smart mobile devices, more and more financial transactions and activities have been digitalized. Compared to traditional financial fraud detection strategies using credit-related features, customers are generating a large amount of unstructured behavioral data every second. In this paper, we propose an Recurrent Neural Netword (RNN) based deep-learning structure integrated with Markov Transition Field (MTF) for predicting online fraud behaviors using customer's interactions with websites or smart-phone apps as a series of states. In practice, we tested and proved that the proposed network structure for processing sequential behavioral data could significantly boost fraud predictive ability comparing with the multilayer perceptron network and distance based classifier with Dynamic Time Warping(DTW) as distance metric.

We present a training framework for neural abstractive summarization based on actor-critic approaches from reinforcement learning. In the traditional neural network based methods, the objective is only to maximize the likelihood of the predicted summaries, no other assessment constraints are considered, which may generate low-quality summaries or even incorrect sentences. To alleviate this problem, we employ an actor-critic framework to enhance the training procedure. For the actor, we employ the typical attention based sequence-to-sequence (seq2seq) framework as the policy network for summary generation. For the critic, we combine the maximum likelihood estimator with a well designed global summary quality estimator which is a neural network based binary classifier aiming to make the generated summaries indistinguishable from the human-written ones. Policy gradient method is used to conduct the parameter learning. An alternating training strategy is proposed to conduct the joint training of the actor and critic models. Extensive experiments on some benchmark datasets in different languages show that our framework achieves improvements over the state-of-the-art methods.

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast capabilities of convolutional neural networks, that can extract useful features from noisy and complex data. Games are excellent tools to test and push the boundaries of novel RL algorithms because they give valuable insight into how well an algorithm can perform in isolated environments without the real-life consequences. Real-time strategy games (RTS) is a genre that has tremendous complexity and challenges the player in short and long-term planning. There is much research that focuses on applied RL in RTS games, and novel advances are therefore anticipated in the not too distant future. However, there are to date few environments for testing RTS AIs. Environments in the literature are often either overly simplistic, such as microRTS, or complex and without the possibility for accelerated learning on consumer hardware like StarCraft II. This paper introduces the Deep RTS game environment for testing cutting-edge artificial intelligence algorithms for RTS games. Deep RTS is a high-performance RTS game made specifically for artificial intelligence research. It supports accelerated learning, meaning that it can learn at a magnitude of 50 000 times faster compared to existing RTS games. Deep RTS has a flexible configuration, enabling research in several different RTS scenarios, including partially observable state-spaces and map complexity. We show that Deep RTS lives up to our promises by comparing its performance with microRTS, ELF, and StarCraft II on high-end consumer hardware. Using Deep RTS, we show that a Deep Q-Network agent beats random-play agents over 70% of the time. Deep RTS is publicly available at https://github.com/cair/DeepRTS.

Running high-resolution physical models is computationally expensive and essential for many disciplines. Agriculture, transportation, and energy are sectors that depend on high-resolution weather models, which typically consume many hours of large High Performance Computing (HPC) systems to deliver timely results. Many users cannot afford to run the desired resolution and are forced to use low resolution output. One simple solution is to interpolate results for visualization. It is also possible to combine an ensemble of low resolution models to obtain a better prediction. However, these approaches fail to capture the redundant information and patterns in the low-resolution input that could help improve the quality of prediction. In this paper, we propose and evaluate a strategy based on a deep neural network to learn a high-resolution representation from low-resolution predictions using weather forecast as a practical use case. We take a supervised learning approach, since obtaining labeled data can be done automatically. Our results show significant improvement when compared with standard practices and the strategy is still lightweight enough to run on modest computer systems.

Approaches to decision-making under uncertainty in the belief function framework are reviewed. Most methods are shown to blend criteria for decision under ignorance with the maximum expected utility principle of Bayesian decision theory. A distinction is made between methods that construct a complete preference relation among acts, and those that allow incomparability of some acts due to lack of information. Methods developed in the imprecise probability framework are applicable in the Dempster-Shafer context and are also reviewed. Shafer's constructive decision theory, which substitutes the notion of goal for that of utility, is described and contrasted with other approaches. The paper ends by pointing out the need to carry out deeper investigation of fundamental issues related to decision-making with belief functions and to assess the descriptive, normative and prescriptive values of the different approaches.

Abstract-- In this paper, we propose an novel implementation of a simultaneous localization and mapping (SLAM) system based on a monocular camera from an unmanned aerial vehicle (UAV) using Depth prediction performed with Capsule Networks (CapsNet), which possess improvements over the drawbacks of the more widely-used Convolutional Neural Networks (CNN). An Extended Kalman Filter will assist in estimating the position of the UAV so that we are able to update the belief for the environment. Results will be evaluated on a benchmark dataset to portray the accuracy of our intended approach. I. INTRODUCTION Simultaneous localization and mapping (SLAM) has a significant role to play in helping autonomous robots to navigate their way around an uncertain environment and this has many widespread implications in various industries. For instance, drones can be programmed to find their way in a logistics warehouse without prior knowledge of the space, in order to retrieve information of a particular package.

Data streams occur widely in various real world applications. The research on streaming data mainly focuses on the data management, query evaluation and optimization on these data, however the work on reasoning procedures for streaming knowledge bases on both the assertional and terminological levels is very limited. Typically reasoning services on large knowledge bases are very expensive, and need to be applied continuously when the data is received as a stream. Hence new techniques for optimizing this continuous process is needed for developing efficient reasoners on streaming data. In this paper, we survey the related research on reasoning on expressive logics that can be applied to this setting, and point to further research directions in this area.

Amputees can be tricked into'feeling' life-like sensations from robotic limbs using virtual reality headsets, according to new research. By combining the senses of sight and touch using the VR headset, scientists were able to convince patients a prosthetic hand belonged to their own body. Patients wore virtual reality goggles which showed the index finger of the prosthetic limb glowing at the same point researchers administered artificial touch sensations. This unique combination of sight and sensation convinced people the prosthetic was a natural extension of their own body. The latest findings could revolutionise treatment of maimed members of the Armed Forces and other people who have lost arms or legs, scientists say.

It seems insects might be able to see much more than we previously thought. New research has revealed that both the honeybees and wasps are able to learn achromatic (black and white) images of human faces. Despite having tiny brains made up of just one million brain cells – compared to the 86 billion that make up a human brain – they appear to visually process faces in a similar way to how we do. This is despite them having no evolutionary reason for doing so, writes Dr Adrian Dyer, an associate professor from RMIT University in Australia for The Conversation. Understanding how this developed could help researchers create smarter artificial intelligence, Dr Dyer says.

Computer-aided diagnosis (CAD) in colonoscopy may provide real-time differentiation between neoplastic polyps requiring resection and non-neoplastic polyps that can safely be left in place, according to a Japanese study in Annals of Internal Medicine. This method allows the complete resection of adenomatous polyps while preventing unnecessary polypectomy of non-neoplastic polyps. As screening for colon cancer increases worldwide, this approach could result in efficiencies and cost savings. Researchers led by Yuichi Mori, MD, PhD, of Showa University Northern Yokohama Hospital in Japan, looked at 791 consecutive patients having colonoscopy at the hospital with a total of 23 endoscopists in the period June to September 2017. Indications for colonoscopy included surveillance (most common), screening, symptom investigations, and planned treatment of other polyps.