Science-fiction visionaries have long promised us all kinds of futuristic transportation options, and while jetpacks and teleportation are still some ways off, the technologies are finally in place to make self-driving cars a reality. It's time for automakers to put the pedal to the metal as they compete with technology companies and other industry disruptors to put partially or fully autonomous vehicles on American roads. The auto industry has a head start: After decades of investments, today's vehicles offer many partially autonomous features like lane departure systems, adaptive cruise control, and emergency braking. Emerging technologies could enable even more vehicle-to-vehicle and vehicle-to-infrastructure connectivity, making the leap to fully driverless cars even smaller. In fact, executives from several leading automakers foresee advanced self-driving technology being available by 2021 or even sooner;1 some envision vehicles without steering wheels or pedals to be driven by advanced technology and sensors and not people.

Foregoing a good night's sleep may wreck the brain's ability to make new memories. A new study from Johns Hopkins University School of Medicine demonstrated that a key purpose of sleep is to recalibrate the brain cells responsible for learning and memory, solidifying lessons learned for when the sleeper is awake. Using a mouse model, the researchers discovered several important molecules that govern the recalibration process, as well as evidence that sleep deprivation, sleep disorders and sleeping pills can interfere with the process. Graham Diering, Ph.D., the postdoctoral fellow who led the study, explained that the results from the mouse study can be used to make determinations about the human brain. "Our findings solidly advance the idea that the mouse and presumably the human brain can only store so much information before it needs to recalibrate," he said in a statement.

Fake News, Cont'd: During a TV interview last night, Trump adviser Kellyanne Conway attempted to defend her boss's travel ban by pointing to "the Bowling Green Massacre"--which never took place. Conway tweeted that she "meant to say'Bowling Green terrorists,'" but her gaffe falls into a larger pattern of the Trump administration's "alternative facts." One true fact about the travel ban is that it revoked 60,000 visas--though a DOJ attorney erroneously said 100,000 earlier today. That error was poorly timed, since there's been a recent increase in fake news aimed at the biases of Trump's detractors as well as his supporters. We talked to Brooke Binkowski of the rumor-debunking site Snopes about the rise of fake news among progressives and what to do about it.

Online health resources aimed at older adults can have a significant impact on patient-physician relationships and on health outcomes. High quality online resources that are delivered in an ethical, emotionally aligned way can increase trust and reduce negative health outcomes such as anxiety. In contrast, low quality or misaligned resources can lead to harmful consequences such as inappropriate use of health care services and poor health decision-making. This paper investigates mechanisms for ensuring both quality and alignment of online health resources and interventions. First, the recently proposed QUEST evaluation instrument is examined. QUEST assesses the quality of online health information along six validated dimensions (authorship, attribution, conflict of interest, currency, complementarity, tone). A decision tree classifier is learned that is able to predict one criteria of the QUEST tool, complementarity, with an F1-score of 0.9 on a manually annotated dataset of 50 articles giving advice about Alzheimer disease. A social-psychological theory of affective (emotional) alignment is then presented, and demonstrated to gauge older adults emotional interpretations of eight examples of health recommendation systems related to Alzheimer disease (online memory tests). The paper concludes with a synthesizing view and a vision for the future of this important societal challenge.

The quality of a good sleep is important for a healthy life. Recently, several sleep analysis products have emerged on the market; however, many of them require additional hardware or there is a lack of scientific evidence regarding their clinical efficacy. We proposed a novel method via clustering of sound events for discovering the sleep pattern. This method extended conventional self-organizing map algorithm by kernelized and sequence-based technologies, obtained a fine-grained map that depicts the distribution and changes of sleep-related events. We introduced widely applied features in sound processing and popular kernel functions to our method, evaluated their performance, and made a comparison. Our method requires few additional hardware, and by visualizing the transition of cluster dynamics, the correlation between sleep-related sound events and sleep stages was revealed.

Alternative energy is becoming a growing source of power in the United States, including wind, hydroelectric and solar. The Solar Decathlon is a competition run by the US Department of Energy every two years. Washington State University (WSU) is one of twenty teams recently selected to compete in the fall 2017 challenge. A central part to WSU's entry is incorporating new and existing smart home technology from the ground up. The smart home can help to optimize energy loads, battery life and general comfort of the user in the home. This paper discusses the high-level goals of the project, hardware selected, build strategy and anticipated approach.

Currently two barriers exist that sabotage clothing semantic parsing research: existing methods are time-consuming and the lack of large publicly available dataset that enables parsing at multiple scales. To mitigate these two dilemmas, we hereby embrace deep learning method and design a lightweight multi-scale inception neural network which is at both inside and outside multi-scale inception during training. Moreover, atrous convolution block is involved to enlarge the field of view while bringing neither extra computation cost nor parameters. Then the pre-trained model is further pruned and compressed by fine-tuning on a lightweight version of the same network used earlier, in which the inactive feature response and connections below a pre-defined threshold are directly removed. Besides, we construct so far the largest fashion guided clothing semantic parsing dataset (FCP) which contains a total of 5,000 clothing images and each image associates with both pixel-level, object-level and image-level annotations. All clothing in the dataset are recommended by fashion experts or trendsetters and contains as many as 65 common clothing items, accessories. We organize the dataset as Wordnet tree structure so that it enables fashionably parsing hierarchically. Finally, we conduct extensive experiments on three currently available datasets. Both quantitative and qualitative results demonstrate the priority and feasibility of our method, comparing with several other deep learning based methods. Our method achieves 35 FPS in a single Nvidia Titian X GPU with only minimal accuracy loss.

We consider the problem of actively eliciting preferences from a human by a planning system. While prior work in planning have explored the use of domain knowledge and preferences, they assume that the knowledge must be provided before the planner starts the planning process. Our work is in building more collaborative systems where a system can solicit advice as needed. We verify empirically that this approach lead to faster and better solutions, while reducing the burden on the human expert.

In this paper, we propose a novel deep manifold clustering (DMC) method for learning effective deep representations and partitioning a dataset into clusters where each cluster contains data points from a single nonlinear manifold. Different from other previous research efforts, we adopt deep neural network to classify and parameterize unlabeled data which lie on multiple manifolds. Firstly, motivated by the observation that nearby points lie on the local of manifold should possess similar representations, a locality preserving objective is defined to iteratively explore data relation and learn structure preserving representations. Secondly, by finding the corresponding cluster centers from the representations, a clustering-oriented objective is then proposed to guide the model to extract both discriminative and cluster-specific representations. Finally, by integrating two objectives into a single model with a unified cost function and optimizing it by using back propagation, we can obtain not only more powerful representations, but also more precise clusters of data. In addition, our model can be intuitively extended to cluster out-of-sample datum. The experimental results and comparisons with existing state-of-the-art methods show that the proposed method consistently achieves the best performance on various benchmark datasets.

The importance of visual context in object recognition has been intensively studied over the years. Along with the advent of deep convolutional neural networks (CNN), using contextual information with such systems starts to receive attention in the literature. Regardless of deep learning advances, aerial image analysis still poses many great challenges. Satellite images are often taken under poor lighting conditions and contain low resolution objects, many times occluded. For this particular task, visual context could be of great help, but there are still very few papers that consider context in aerial image understanding. Our work addresses the task of object segmentation in aerial images with a novel dual-stream deep convolutional neural network that integrates the local object appearance and global contextual information into a unified network. Our model learns to combine local object appearance and global semantic knowledge simultaneously and in a complementary way, so that together they form a powerful classifier. Experiments on the Massachusetts Buildings Dataset demonstrate the superiority of our model over state-of-the-art methods. We also introduce two new challenging datasets for the task of buildings and road segmentation. While our local-global model could also be useful in general recognition tasks, we clearly demonstrate the effectiveness of visual context in conjunction with deep nets in aerial image understanding.