--Due to the drastic increase of mobile traffic, wireless caching is proposed to serve repeated requests for content download. T o determine the caching scheme for decentralized caching networks, the content preference learning problem based on mobility prediction is studied. We first formulate preference prediction as a decentralized regularized multi-task learning (DRMTL) problem without considering the mobility of mobile terminals (MTs). The problem is solved by a hybrid Jacobian and Gauss-Seidel proximal multi-block alternating direction method (ADMM) based algorithm, which is proven to conditionally converge to the optimal solution with a rate O (1 / k) . Then we use the tool of Markov renewal process to predict the moving path and sojourn time for MTs, and integrate the mobility pattern with the DRMTL model by reweighting the training samples and introducing a transfer penalty in the objective. We solve the problem and prove that the developed algorithm has the same convergence property but with different conditions. Through simulation we show the convergence analysis on proposed algorithms. Our real trace driven experiments illustrate that the mobility-aware DRMTL model can provide a more accurate prediction on geography preference than DRMTL model. Besides, the hit ratio achieved by most popular proactive caching (MPC) policy with preference predicted by mobility-aware DRMTL outperforms the MPC with preference from DRMTL and random caching (RC) schemes. As a promising technology for the fifth-generation (5G) wireless networks and beyond, proactive caching can alleviate the heavy traffic burden on backhaul links and reduce service delay, through proactively storing popular contents at base stations (BSs) and mobile terminals (MTs) [1]-[3]. With the limitation of storage memory, determining where and what to cache in content centric wireless networks becomes one of the main challenges in the design of proactive caching schemes. Among the various factors affecting the wireless caching design, involving the mobility of MTs and learning content preference are two critical challenges, which have attracted more and more research interest recently. A. background Current investigation on mobility aware wireless caching mainly includes two aspects: studying the impact of MT mobility on caching schemes [4]-[7], and optimizing the wireless caching schemes based on the mobility information of MTs Y u Y e, Ming Xiao and Mikael Skoglund are with the School of Electrical Engineering and Computer Science, Royal Institute of Technology (KTH), Stockholm, Sweden (email: yu9@kth.se,

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models' composition operations are local or global (iv) if models' predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during training. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET and apply the resulting tests to three popular sequence-to- sequence models: a recurrent, a convolution based and a transformer model. We provide an in depth analysis of the results, that uncover the strengths and weaknesses of these three architectures and point to potential areas of improvement.

The battery is a key component of autonomous robots. Its performance limits the robot's safety and reliability. Unlike liquid-fuel, a battery, as a chemical device, exhibits complicated features, including (i) capacity fade over successive recharges and (ii) increasing discharge rate as the state of charge (SOC) goes down for a given power demand. Existing formal verification studies of autonomous robots, when considering energy constraints, formalise the energy component in a generic manner such that the battery features are overlooked. In this paper, we model an unmanned aerial vehicle (UA V) inspection mission on a wind farm and via probabilistic model checking in PRISM show (i) how the battery features may affect the verification results significantly in practical cases; and (ii) how the battery features, together with dynamic environments and battery safety strategies, jointly affect the verification results. Potential solutions to explicitly integrate battery prognostics and health management (PHM) with formal verification of autonomous robots are also discussed to motivate future work. Keywords: Formal verification · Probabilistic model checking · PRISM · Autonomous systems · Unmanned aerial vehicle · Battery PHM. 1 Introduction Autonomous robots, such as unmanned aerial vehicles (UA V) (commonly termed drones 3), unmanned underwater vehicles (UUV), self-driving cars and legged-robots, obtain increasingly widespread applications in many domains [14].

In [1], we have explored the theoretical aspects of feature selection and evolutionary algorithms. In this chapter, we focus on optimization algorithms for enhancing data analytic process, i.e., we propose to explore applications of nature-inspired algorithms in data science. Feature selection optimization is a hybrid approach leveraging feature selection techniques and evolutionary algorithms process to optimize the selected features. Prior works solve this problem iteratively to converge to an optimal feature subset. Feature selection optimization is a non-specific domain approach. Data scientists mainly attempt to find an advanced way to analyze data n with high computational efficiency and low time complexity, leading to efficient data analytics. Thus, by increasing generated/measured/sensed data from various sources, analysis, manipulation and illustration of data grow exponentially. Due to the large scale data sets, Curse of dimensionality (CoD) is one of the NP-hard problems in data science. Hence, several efforts have been focused on leveraging evolutionary algorithms (EAs) to address the complex issues in large scale data analytics problems. Dimension reduction, together with EAs, lends itself to solve CoD and solve complex problems, in terms of time complexity, efficiently. In this chapter, we first provide a brief overview of previous studies that focused on solving CoD using feature extraction optimization process. We then discuss practical examples of research studies are successfully tackled some application domains, such as image processing, sentiment analysis, network traffics / anomalies analysis, credit score analysis and other benchmark functions/data sets analysis.

In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction. However, the traditional prediction models are fixed while the conditions of the machines change over time, thus making the errors of predictions increase with the lapse of time. In this paper, we propose a general data renewal model to deal with it. Combined with the similarity function and the loss function, it estimates the time of updating the existing prediction model, then updates it according to the evaluation function iteratively and adaptively. We have applied the data renewal model to two prediction algorithms. The experiments demonstrate that the data renewal model can effectively identify the changes of data, update and optimize the prediction model so as to improve the accuracy of prediction.

We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architecture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements a form of transfer learning, permitting to train on a few source domains, then generalize to new target domains, without learning on any example of that domain. We evaluate the viability of this technique to rapidly assess curative actions that human operators take in emergency situations, using real historical data, from the French high voltage power grid.Figure 1: Electricity is transported from production nodes (top) to consumption nodes (bottom), through lines (green and red edges) connected at substations (black circles), forming a transmission grid of a given topology τ . Injections x ( x 1, x 2, x 3, x 4) (production or consumption) add up to zero.

Road extraction from very high resolution satellite images is one of the most important topics in the field of remote sensing. For the road segmentation problem, spatial properties of the data can usually be captured using Convolutional Neural Networks. However, this approach only considers a few local neighborhoods at a time and has difficulty capturing long-range dependencies. In order to overcome the problem, we propose Non-Local LinkNet with non-local blocks that can grasp relations between global features. It enables each spatial feature point to refer to all other contextual information and results in more accurate road segmentation. In detail, our method achieved 65.00\% mIOU scores on the DeepGlobe 2018 Road Extraction Challenge dataset. Our best model outperformed D-LinkNet, 1st-ranked solution, by a significant gap of mIOU 0.88\% with much less number of parameters. We also present empirical analyses on proper usage of non-local blocks for the baseline model.

Robust automation of analysis procedures capable of handling diverse data sets is critical for high data throughput experiments at the Linac Coherent Light Source (LCLS). One challenge encountered in this process is determining the number of clusters required for the execution of conventional clustering algorithms. It is demonstrated here that bi-cross validation of the inverted and regularized Laplacian, used in the spectral clustering algorithm, yields a robust minimum at the predicted number of clusters and kernel hyper parameters. These results indicate that the process of estimating the number of clusters should not be divorced from the process of estimating other hyper parameters. Applying this method to LCLS xray scattering data demonstrates the ability to identify clusters of dropped shots without manually setting boundaries on detector fluence and provides a path towards identifying rare events.

One of the most common criticisms of machine learning is an assumed inability for models to extrapolate, i.e. to identify extraordinary materials with properties beyond those present in the training data set. To investigate whether this is indeed the case, this work takes advantage of density functional theory calculated properties (bulk modulus, shear modulus, thermal conductivity, thermal expansion, band gap and Debye temperature) to investigate whether machine learning is truly capable of predicting materials with properties that extend beyond previously seen values. We refer to these materials as extraordinary, meaning they represent the top 1% of values in the available data set. Interestingly, we show that even when machine learning is trained on a fraction of the bottom 99% we can consistently identify 3/4 of the highest performing compositions for all considered properties with a precision that is typically above 0.5. Moreover, we investigate a few different modeling choices and demonstrate how a classification approach can identify an equivalent amount of extraordinary compounds but with significantly fewer false positives than a regression approach.

In light of this, Roope Tervo, a software architect at the Finnish Meteorological Institute (FMI) and PhD researcher at Aalto university in Professor Alex Jung's research group, has conceived of a machine learning approach to predict how severe storms may be. To achieve this Tervo first fed the system data from power-outages. "Storms were sorted into 4 classes. A class 1 storm cut-off up to 10% of transformers, a class 2 up to 50%, and a class 3 storm cut power to over 50% of the transformers," revealed an Aalto University statement. Secondly, Tervo took the data from the storms and made it easy for the computer to understand.