We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory. While the primary goal of RFF is to approximate a kernel, we look at the Fourier transform as a prior distribution over trigonometric hypotheses. It naturally suggests learning a posterior on these hypotheses. We derive generalization bounds that are optimized by learning a pseudo-posterior obtained from a closed-form expression. Based on this study, we consider two learning strategies: The first one finds a compact landmarks-based representation of the data where each landmark is given by a distribution-tailored similarity measure, while the second one provides a PAC-Bayesian justification to the kernel alignment method of Sinha and Duchi (2016).

Convolutional neural networks (CNNs) attained a good performance in hyperspectral sensing image (HSI) classification, but CNNs consider spectra as orderless vectors. Therefore, considering the spectra as sequences, recurrent neural networks (RNNs) have been applied in HSI classification, for RNNs is skilled at dealing with sequential data. However, for a long-sequence task, RNNs is difficult for training and not as effective as we expected. Besides, spatial contextual features are not considered in RNNs. In this study, we propose a Shorten Spatial-spectral RNN with Parallel-GRU (St-SS-pGRU) for HSI classification. A shorten RNN is more efficient and easier for training than band-by-band RNN. By combining converlusion layer, the St-SSpGRU model considers not only spectral but also spatial feature, which results in a better performance. An architecture named parallel-GRU is also proposed and applied in St-SS-pGRU. With this architecture, the model gets a better performance and is more robust.

In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a single network, trained using only a single cost function: maximizing the likelihood of the training data, which makes the training procedure simple and stable. Our PyTorch implementation produces audio samples at a rate of more than 500 kHz on an NVIDIA V100 GPU. Mean Opinion Scores show that it delivers audio quality as good as the best publicly available WaveNet implementation. All code will be made publicly available online.

Human decision-makers are very good at taking decisions under rather imprecise specification of the decision-making problem, both in terms of constraints as well as objective. One 1 might argue that the human decision-maker can pretty reliably learn from observed previous decisions - a traditional learning-by-example setup. At the same time, when we try to turn these decision-making problems into actual optimization problems, we often run into all types of issues in terms of specifying the model. In an optimal world, we would be able to infer or learn the optimization problem from previously observed decisions taken by an expert. This problem naturally occurs in many settings where we do not have direct access to the decision-maker's preference or objective function but can observe his behaviour, and where the learner as well as the decision-maker have access to the same information. Natural examples are as diverse as making recommendations based on user history and strategic planning problems, where the agent's preferences are unknown but the system is observable. Other examples include knowledge transfer from a human planner into a decision support system: often human operators have arrived at finely-tuned "objective functions" through many years of experience, and in many cases it is desirable to replicate the decision-making process both for scaling up and also for potentially including it in large-scale scenario analysis and simulation to explore responses under varying conditions. Here we consider the learning of preferences or objectives from an expert by means of observing his actions.

Recently, data mining studies are being successfully conducted to estimate several parameters in a variety of domains. Data mining techniques have attracted the attention of the information industry and society as a whole, due to a large amount of data and the imminent need to turn it into useful knowledge. However, the effective use of data in some areas is still under development, as is the case in sports, which in recent years, has presented a slight growth; consequently, many sports organizations have begun to see that there is a wealth of unexplored knowledge in the data extracted by them. Therefore, this article presents a systematic review of sports data mining. Regarding years 2010 to 2018, 31 types of research were found in this topic. Based on these studies, we present the current panorama, themes, the database used, proposals, algorithms, and research opportunities. Our findings provide a better understanding of the sports data mining potentials, besides motivating the scientific community to explore this timely and interesting topic.

Abstract--This paper investigates the vision-based autonomous driving with deep learning and reinforcement learning methods. Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a perception module and a control module. The perception module which is based on a multi-task learning neural network first takes a driver-view image as its input and predicts the track features. The control module which is based on reinforcement learning then makes a control decision based on these features. In order to improve the data efficiency, we propose visual TORCS (VTORCS), a deep reinforcement learning environment which is based on the open racing car simulator (TORCS). By means of the provided functions, one can train an agent with the input of an image or various physical sensor measurement, or evaluate the perception algorithm on this simulator. The trained reinforcement learning controller outperforms the linear quadratic regulator (LQR) controller and model predictive control (MPC) controller on different tracks. The experiments demonstrate that the perception module shows promising performance and the controller is capable of controlling the vehicle drive well along the track center with visual input. N recent years, artificial intelligence (AI) has flourished in many fields such as autonomous driving [1] [2], games [3] [4], and engineering applications [5] [6]. As one of the most popular topics, autonomous driving has drawn great attention both from the academic and industrial communities and is thought to be the next revolution in the intelligent transportation system. The autonomous driving system mainly consists of four modules: an environment perception module, a trajectory planning module, a control module, and an actuator mechanism module. The initial perception methods [7] [8] are based on the expensive LIDARs which usually cost tens of thousands of dollars. The high cost limits their large-scale applications to the ordinary vehicles. Recently, more attention is paid to the image-based methods [9] of which the core sensor, i.e. camera is relatively cheap and already equipped on most vehicles. Some of these perception methods have been developed into products [10] [11]. In this paper, we focus on the lateral control problem based on the image captured by the onboard camera.

Abstract--Advanced automation is involved in information collection and evaluation, in decision-making and in the implementation of chosen actions. In such systems, human responsibility becomes equivocal, and there may exist a responsibility gap. Understanding human responsibility is particularly important when systems can harm people, as with autonomous vehicles or, most notably, with Autonomous Weapon Systems (AWS). Using Information Theory, we develop a responsibility quantification (ResQu) model of human interaction in automated systems and demonstrate its applications on decisions involving AWS. The analysis reveals that human comparative responsibility is often low, even when major functions are allocated to the human. Thus, broadly stated policies of keeping humans in the loop and having meaningful human control are misleading and cannot truly direct decisions on how to involve humans in advanced automation. Our responsibility model can guide system design decisions and can aid policy and legal decisions regarding human responsibility in highly automated systems. Financial markets largely function through algorithmic trading mechanisms [1, 2], semiconductor manufacturing is almost entirely automated [3], and decision support systems and aids for diagnostic interpretation have become part of medical practice [4, 5]. Similarly, in aviation, flight management systems control almost all parts of the flight [6, 7], and in surface transportation, public transportation is increasingly automated, and the first autonomous cars appear on public roads [8, 9]. Manuscript submitted October 30, 2018; (Corresponding author: Joachim Meyer) N. Douer with the Department of Industrial Engineering at Tel Aviv University, Ramat Aviv, Tel Aviv 69978, Israel (email: nirdouer@mail.tau.ac.il).

This paper presents the self-organized neuromorphic architecture named SOMA. The objective is to study neural-based self-organization in computing systems and to prove the feasibility of a self-organizing hardware structure. Considering that these properties emerge from large scale and fully connected neural maps, we will focus on the definition of a self-organizing hardware architecture based on digital spiking neurons that offer hardware efficiency. From a biological point of view, this corresponds to a combination of the so-called synaptic and structural plasticities. We intend to define computational models able to simultaneously self-organize at both computation and communication levels, and we want these models to be hardware-compliant, fault tolerant and scalable by means of a neuro-cellular structure.

AI'deep fake' software that can be used to make bogus videos that'threaten democracy' is being funded by a UK government research body. The AI technology - which has been described as a'propaganda weapon' - can mimic facial expressions and make it look like someone is saying something they're not. People are concerned it could be used to create fake news clips that falsely put words into the mouths of politicians or other powerful figures. The British firm developing this technology received £70,000 ($90,000) from a government-funded organisation this year, a new report has revealed. The AI technology (stock image) - which has been described as a'propaganda weapon - can mimic facial expressions and make it look like someone is saying something they're not Damian Collins, who chairs a UK select committee on fake news said deep fakes were'one of the most serious threats that democracy faces'.

Humans have a '50/50' chance of finding life on the red planet within three years, according to an astrobiologist working on the next Mars rover. The ExoMars rover is scheduled to land on the red planet in August 2021 and will be part of a mission to investigate how the planet evolved and whether it has conditions for life. Scientists working on the project believe plans to excavate below the surface of the red planet greatly increase their chance of finding life. Humans have a '50/50' chance of finding life on the red planet within three years, according to an astrobiologist working on the next Mars rover (artist's impression) Due to launch in 2020, the ExoMars rover will be the first of its kind to travel across the martian surface and drill-down to determine if evidence of life is buried underground. Dr Susanne Schwenzer, the astrobiologist on the ExoMars rover told the Daily Telegraph that the'chances are just about 50/50'.