Abstract--Distributed gradient descent (DGD) is an efficient way of implementing gradient descent (GD), especially for large data sets, by dividing the computation tasks into smaller sub-tasks and assigning to different computing servers (CSs) to be executed in parallel. In standard parallel execution, per-iteration waiting time is limited by the execution time of the straggling servers. Coded DGD techniques have been introduced recently, which can tolerate straggling servers via assigning redundant computation tasks to the CSs. In most of the existing DGD schemes, either with coded computation or coded communication, the non-straggling CSs transmit one message per iteration once they complete all their assigned computation tasks. However, although the straggling servers cannot complete all their assigned tasks, they are often able to complete a certain portion of them. In this paper, we allow multiple transmissions from each CS at each iteration in order to make sure a maximum number of completed computations can be reported to the aggregating server (AS), including the straggling servers. We numerically show that the average completion time per iteration can be reduced significantly by slightly increasing the communication load per server . Index Terms --Distributed gradient descent, coded computation, coded gradient, polynomial codes, maximum-distance separable codes.

If you suffer with a short temper – you're probably not as smart as you think you are, a new study has found. Angry people are more likely to overestimate their intelligence levels than those with a calmer disposition, scientists have found. That's because being angry is linked with high levels of narcissism, as well as a greater belief in their abilities and competence. Those with a short fuse were also more likely to have problems maintaining a stable relationship, according to the latest findings. This is because individuals with high levels of narcissism struggle to establish bonds with others as they are always trying to dominate them.

In 2017, the Australian military drone-racing team made its competitive debut during the Australian Drone Nationals. Given the technology's long history within the military, you might think they would have an edge. But that's not what happened. Drone racing is a fairly new sport that merges video game racing with real-life drone flying. Racers put on a pair of first-person view (or FPV) goggles, which allow them to see exactly what they would if they were sitting in the teeny-tiny cockpit.

Conventional approaches used supervised learning to estimate off-line writer identifications. In this study, we improved the off-line writer identifica- tions by semi-supervised feature learning pipeline, which trained the extra unla- beled data and the original labeled data simultaneously. In specific, we proposed a weighted label smoothing regularization (WLSR) method, which assigned the weighted uniform label distribution to the extra unlabeled data. We regularized the convolutional neural network (CNN) baseline, which allows learning more discriminative features to represent the properties of different writing styles. Based on experiments on ICDAR2013, CVL and IAM benchmark datasets, our results showed that semi-supervised feature learning improved the baseline meas- urement and achieved better performance compared with existing writer identifications approaches.

The concept of stochastic configuration networks (SCNs) others a solid framework for fast implementation of feedforward neural networks through randomized learning. Unlike conventional randomized approaches, SCNs provide an avenue to select appropriate scope of random parameters to ensure the universal approximation property. In this paper, a deep version of stochastic configuration networks, namely deep stacked stochastic configuration network (DSSCN), is proposed for modeling non-stationary data streams. As an extension of evolving stochastic connfiguration networks (eSCNs), this work contributes a way to grow and shrink the structure of deep stochastic configuration networks autonomously from data streams. The performance of DSSCN is evaluated by six benchmark datasets. Simulation results, compared with prominent data stream algorithms, show that the proposed method is capable of achieving comparable accuracy and evolving compact and parsimonious deep stacked network architecture.

Abstract-- Driving is a social activity: drivers often indicate their intent to change lanes via motion cues. We consider mixed-autonomy traffic where a Human-driven V ehicle (HV) and an Autonomous V ehicle (A V) drive together . We propose a planning framework where the degree to which the A V considers the other agent's reward is controlled by a selfishness factor . We test our approach on a simulated two-lane highway where the A V and HV merge into each other's lanes. In a user study with 21 subjects and 6 different selfishness factors, we found that our planning approach was sound and that both agents had less merging times when a factor that balances the rewards for the two agents was chosen. Our results on double lane merging suggest it to be a nonzero-sum game and encourage further investigation on collaborative decision making algorithms for mixed-autonomy traffic. Driving is a social activity: drivers indicate their willingness to change lanes by subtle cues such as eye contact, or by not-so-subtle cues such as adjusting their speed and position [1]. There has been impressive demonstrations of Autonomous V ehicle (A V) technology [2]-[4], however one of the remaining challenges in this area is reading those cues to estimate the intentions of other agents as well as using cues to communicate the intentions of the A V . As A Vs become commonplace, the situations where A V's and Human-driven V ehicles (HV) interact will increase.

By now we should have an understanding of what artificial intelligence (AI) is capable of today, and what it could accomplish in the future. Now, the latest possible thing AI could do in the future, according to one study, is to predict human personality traits. A recent study done by the University of South Australia has shown that artificial intelligence is capable of telling the type of personality traits that live inside any human being. To accomplish this, the university tracked the eye movements of 42 participants while they go about their daily lives. Now, before the subjects were made to live with an AI watching their every move, they were required to take part in a personality questionnaire.

Time travel and unchaining the time-matter continuum is no big deal. Nor is recruiting a dragon slayer, a Jedi Knight and a Transformer – a child's mind is able to create fantastic worlds in seconds. So what would happen if robots had an artificial imagination? Developing innovative strategies in Go or unorthodox approaches to chess are just top-of-mind examples of how the agent in reinforcement learning can be creative. Go, Chess and League of Legends all draw on the imagination: players use abstract thinking to predict their opponent's actions and construct a strategy for upcoming moves.

Often referred to as the Amazon of China, JD.com started in 1998 as a brick-and-mortar store in Beijing, but it has aspirations to be the world's leading e-commerce retailer. Based on its tremendous growth, it might not take long for the company to get there. Richard Liu, the company's founder, CEO, and chairman, has even gone so far to predict his company won't need humans and said, "I hope my company would be 100% automation someday…no human beings anymore, 100% operated by AI and robots." JD.com and its competitors such as Amazon, Alphabet, Tencent, Alibaba and more are not only racing to be the world's largest e-commerce business but to create the operating system for retail in the future. JD.com is driving business with artificial intelligence, big data, and robotics while building the retail infrastructure for the 4th industrial revolution.

When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of $X$ conditional on $Y = 1$, where X stands for the feature and Y the label. Most existing algorithms are optimally designed under the assumption. However, for many real-world applications, the observed positive examples are dependent on the conditional probability $P(Y = 1|X)$ and should be sampled biasedly. In this paper, we assume that a positive example with a higher $P(Y = 1|X)$ is more likely to be labelled and propose a probabilistic-gap based PU learning algorithms. Specifically, by treating the unlabelled data as noisy negative examples, we could automatically label a group positive and negative examples whose labels are identical to the ones assigned by a Bayesian optimal classifier with a consistency guarantee. The relabelled examples have a biased domain, which is remedied by the kernel mean matching technique. The proposed algorithm is model-free and thus do not have any parameters to tune. Experimental results demonstrate that our method works well on both generated and real-world datasets.