Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compression becomes extremely important. However, existing work did not study this problem well because the lack of considering the diversity of dataflow types in hardware architectures. In this paper, we propose EDCompress, an Energy-aware model compression method for various Dataflows. It can effectively reduce the energy consumption of various edge devices, with different dataflow types. Considering the very nature of model compression procedures, we recast the optimization process to a multi-step problem, and solve it by reinforcement learning algorithms. Experiments show that EDCompress could improve 20X, 17X, 37X energy efficiency in VGG-16, MobileNet, LeNet-5 networks, respectively, with negligible loss of accuracy. EDCompress could also find the optimal dataflow type for specific neural networks in terms of energy consumption, which can guide the deployment of CNN models on hardware systems.

Polymeric membranes assist with a wide variety of tasks, including water filtration and gas-vapor separation. Designing a membrane for the desired function is more time-consuming than people may expect. However, researchers at Columbia Engineering, Germany's Max Planck Society and the University of South Carolina applied data science to the task to streamline their efforts. More specifically, they combined big data with machine learning to strategically design polymer membranes to act as gas filters. People frequently depend on plastic films and membranes to separate mixtures of simple cases, such as carbon dioxide and methane.

A battery pioneer has invented a new kind of battery that is 90 per cent cheaper to produce than standard lithium-ion batteries, and potentially much safer. Hideaki Horie – who has worked on battery technology since 1990 and led Nissan's development of the Leaf electric car – discovered a way to replace the batteries basic components in order to speed up and simplify the manufacturing process. "The problem with making lithium batteries now is that it's device manufacturing, like semiconductors," Mr Horie told The Japan Times. "Our goal is to make it more like steel production." Manufacturing the new batteries is significantly simplified by replacing the metal-lined electrodes and liquid electrolytes typically found within lithium-ion units with a resin construction.

This paper serves as an introduction and overview of the potentially useful models and methodologies from artificial intelligence (AI) into the field of transportation engineering for autonomous vehicle (AV) control in the era of mixed autonomy. We will discuss state-of-the-art applications of AI-guided methods, identify opportunities and obstacles, raise open questions, and help suggest the building blocks and areas where AI could play a role in mixed autonomy. We divide the stage of autonomous vehicle (AV) deployment into four phases: the pure HVs, the HV-dominated, the AVdominated, and the pure AVs. This paper is primarily focused on the latter three phases. It is the first-of-its-kind survey paper to comprehensively review literature in both transportation engineering and AI for mixed traffic modeling. Models used for each phase are summarized, encompassing game theory, deep (reinforcement) learning, and imitation learning. While reviewing the methodologies, we primarily focus on the following research questions: (1) What scalable driving policies are to control a large number of AVs in mixed traffic comprised of human drivers and uncontrollable AVs? (2) How do we estimate human driver behaviors? (3) How should the driving behavior of uncontrollable AVs be modeled in the environment? (4) How are the interactions between human drivers and autonomous vehicles characterized? Hopefully this paper will not only inspire our transportation community to rethink the conventional models that are developed in the data-shortage era, but also reach out to other disciplines, in particular robotics and machine learning, to join forces towards creating a safe and efficient mixed traffic ecosystem.

Electronically excited states of molecules are at the heart of photochemistry, photophysics, as well as photobiology and also play a role in material science. Their theoretical description requires highly accurate quantum chemical calculations, which are computationally expensive. In this review, we focus on how machine learning is employed not only to speed up such excited-state simulations but also how this branch of artificial intelligence can be used to advance this exciting research field in all its aspects. Discussed applications of machine learning for excited states include excited-state dynamics simulations, static calculations of absorption spectra, as well as many others. In order to put these studies into context, we discuss the promises and pitfalls of the involved machine learning techniques. Since the latter are mostly based on quantum chemistry calculations, we also provide a short introduction into excited-state electronic structure methods, approaches for nonadiabatic dynamics simulations and describe tricks and problems when using them in machine learning for excited states of molecules.

We generalize a graph-based multiclass semi-supervised classification technique based on diffuse interface methods to multilayer graphs. Besides the treatment of various applications with an inherent multilayer structure, we present a very flexible approach that interprets high-dimensional data in a low-dimensional multilayer graph representation. Highly efficient numerical methods involving the spectral decomposition of the corresponding differential graph operators as well as fast matrix-vector products based on the nonequispaced fast Fourier transform (NFFT) enable the rapid treatment of large and high-dimensional data sets. We perform various numerical tests putting a special focus on image segmentation. In particular, we test the performance of our method on data sets with up to 10 million nodes per layer as well as up to 104 dimensions resulting in graphs with up to 52 layers. While all presented numerical experiments can be run on an average laptop computer, the linear dependence per iteration step of the runtime on the network size makes the algorithm scalable to even larger and higher-dimensional problems.

Convolutional Neural Networks (CNN) possess many positive qualities when it comes to spatial raster data. Translation invariance enables CNNs to detect features regardless of their position in the scene. However, in some domains, like geospatial, not all locations are exactly equal. In this work, we propose localized convolutional neural networks that enable convolutional architectures to learn local features in addition to the global ones. We investigate their instantiations in the form of learnable inputs, local weights, and a more general form. They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed. In this work we address spatio-temporal prediction: test the effectiveness of our methods on a synthetic benchmark dataset and tackle three real-world wind prediction datasets. For one of them, we propose a method to spatially order the unordered data. We compare the recent state-of-the-art spatio-temporal prediction models on the same data. Models that use convolutional layers can be and are extended with our localizations. In all these cases our extensions improve the results, and thus often the state-of-the-art. We share all the code at a public repository.

Managing electrical energy consumption is crucial, simply because of one fact: Electricity cannot be stored, unless converted to other forms. It is best for produced electricity to be instantly consumed; otherwise, additional resources and costs are incurred to store convert and store the excess energy. Energy-efficient buildings provide both economic and environmental benefits, maximising profits and social welfare. Conversely, underestimating energy consumption could be fatal, with excess demand overloading the supply line and even causing blackouts, leading to operational downtime. Clearly, there are tangible benefits in closely monitoring the energy consumption of buildings -- be they office, commercial or household. With the advent of machine learning and data science, accurately predicting future energy consumption becomes increasingly possible. This provides two-fold benefits: firstly, managers gain key insights into factors affecting their building's energy demand, providing opportunities to address them and improve energy efficiency. Not only that, forecasts provide a benchmark to single out anomalously high/low energy consumption and alert managers to faults within the building.

Artificial intelligence has a terrible carbon footprint. Researchers at Stanford University, Facebook AI Research, and Canada's McGill University have developed a tool to measure the hidden cost of machine learning. The "experiment impact tracker" quantifies how much electricity a machine learning project will consume, and its cost in carbon emissions. The team first measured the energy cost of a specific artificial intelligence (AI) model--a challenge because a single machine often trains several models concurrently, while each session also draws power for shared overhead functions like data storage and cooling. The researchers then translated power consumption into carbon emissions, whose blend of renewable and fossil fuels varies by location and time of day, by tapping into public sources about this energy mix.

Artificial Intelligence (AI) has arrived. It is not science fiction anymore. Computers already recognize objects in images and understand speech and language at least as well as, if not better than, humans. This has been made possible with rapid advances in hardware, vast amounts of training data, and innovations in machine learning algorithms such as deep neural networks. Deep learning is the driving force behind the current AI revolution and is giving intelligence to today's self-driving cars, smartphone and smart speakers, and making deep inroads into radiology and even gaming.