This paper studies the problem of {\em learning} the probability distribution $P_X$ of a discrete random variable $X$ using indirect and sequential samples. At each time step, we choose one of the possible $K$ functions, $g_1, \ldots, g_K$ and observe the corresponding sample $g_i(X)$. The goal is to estimate the probability distribution of $X$ by using a minimum number of such sequential samples. This problem has several real-world applications including inference under non-precise information and privacy-preserving statistical estimation. We establish necessary and sufficient conditions on the functions $g_1, \ldots, g_K$ under which asymptotically consistent estimation is possible. We also derive lower bounds on the estimation error as a function of total samples and show that it is order-wise achievable. Leveraging these results, we propose an iterative algorithm that i) chooses the function to observe at each step based on past observations; and ii) combines the obtained samples to estimate $p_X$. The performance of this algorithm is investigated numerically under various scenarios, and shown to outperform baseline approaches.

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.

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.

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.

Summary: There are some interesting use cases where combining CNNs and RNN/LSTMs seems to make sense and a number of researchers pursuing this. However, the latest trends in CNNs may make this obsolete. There are things that just don't seem to go together. Take oil and water for instance. Both valuable, but try putting them together?

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.

Global warming is destroying Earth's coral reefs -- the colorful underwater ecosystems simply can't survive as the ocean warms and acidifies. However, researchers have now discovered a type of coral off the coast of Indonesia's Sulawesi Island that seems to be resistant to global warming. The discovery could help us ensure at least some of the world's coral reefs survive climate change. As part of 50 Reefs, an initiative designed to identify climate change-resistant corals, researchers spent six weeks in June and July using underwater scooters equipped with 360-degree cameras to take more than 56,000 images of shallow water reefs. In total, they snapped images of 3,851 square kilometers (1,487 square miles) worth of reefs.

The most intuitive application of artificial intelligence technology is to bring convenience to our daily lives. So far, the world has seen a multitude of intelligent voice-activated assistants that book hotels, handle logistics, incorporate face recognition technology and enable cars to drive autonomously. The number of new AI companies has grown rapidly in recent years and China ranks second in the global market with close to 1,500 AI companies across the country. No wonder French newspaper "Le Monde" published an article saying that artificial intelligence's "Silicon Valley" will develop in China. In addition to investing heavily in artificial intelligence talent, major companies have also started an acquisition frenzy of artificial intelligence startups.