With the emergence of batteryless computing platforms, we are now able to execute computer programs on embedded systems that do not require a dedicated energy source. These platforms are typically used in sensing applications [30, 39, 70, 73, 79], and their hardware architecture consists primarily of a sensor-enabled microcontroller that is powered by some form of harvested energy such as solar, RF or piezoelectric [63]. Programs that run on these platforms follow the so-called intermittent computing paradigm [50, 52, 75, 77] where a system pauses and resumes its code execution based on the availability of harvested energy. Over the past decade, the efficiency of batteryless computing platforms has been improved by reducing their energy waste through hardware provisioning, through check-pointing [64] to avoid restarting code execution from the beginning at each power-up [8], and through discarding stale sensor data [34] which are no longer useful. Despite these advancements, the capability of batteryless computing platforms has remained limited to simple sensing applications only. In this paper, we introduce the concept of intermittent learning (Figure 1) which makes energy harvested embedded systems capable of executing lightweight machine learning tasks. Their ability to run machine learning tasks inside energy harvesting microcontrollers pushes the boundary of batteryless computing as these devices are able to sense, learn, infer, and evolve over a prolonged lifetime. The proposed intermittent learning paradigm enables a true lifelong learning experience in mobile and embedded systems and advances sensor systems from being smart to smarter. Once deployed in the field, an intermittent learner classifies sensor data as well as learns from them to update the classifier at run-time--without requiring any help from any external system.

In decision making problems for continuous state and action spaces, linear dynamical models are widely employed. Specifically, policies for stochastic linear systems subject to quadratic cost functions capture a large number of applications in reinforcement learning. Selected randomized policies have been studied in the literature recently that address the trade-off between identification and control. However, little is known about policies based on bootstrapping observed states and actions. In this work, we show that bootstrap-based policies achieve a square root scaling of regret with respect to time. We also obtain results on the accuracy of learning the model's dynamics. Corroborative numerical analysis that illustrates the technical results is also provided.

This post was done in partnership with Wirecutter. When readers choose to buy Wirecutter's independently chosen editorial picks, Wirecutter and Engadget may earn affiliate commission. If you want to see who's on the other side of your door without having to get up and look yourself, then the Ring Video Doorbell 2 is the best choice for most everyone. It lets you screen (and record) visitors and keep an eye out for package deliveries. Motion and ring alerts to a smartphone are typically fast, audio and 1080p video are clear, and the Ring 2 can be powered by either standard doorbell wiring or a removable rechargeable battery. The Ring Video Doorbell 2 performs like a cross between a modestly aggressive guard dog and a trusty digital butler. In addition to notifying you--audibly and via smartphone--of activity, it records all motion events to the cloud, letting you view those recordings (as well as live video) on your phone or computer any time. It's also compatible with a good number of smart-home devices, platforms, and monitored security systems. Though video recording and storage require a subscription, the $30 annual fee (a mere 8¢ per day) for 60 days of unlimited video storage is downright cheap compared with the competition. We like the Ring Video Doorbell Pro for all the reasons we like the Ring 2. Additionally, it has a much slimmer and sleeker design that will fit in more doorframes and includes the option for customized motion-detection zones.

A natural gas fired turbine, manufactured by Caterpillar Inc. subsidiary Solar Turbines Inc., runs a compressor at a Williston Basin Interstate Pipeline Co., a subsidiary of MDU Resources Group Inc., natural gas compression station in Bismarck, North Dakota. In the world of oil and natural gas, engineers, geologists, and drilling and production departments tend to get the lion's share of the credit when good things happen, and most of the blame when they don't. That's fair, given the crucial roles these groups of employees play within the thousands of companies that make up the U.S. oil and gas industry. But in recent years, as overall domestic production has risen at a pace no one could have foreseen even five years ago, the credit has begun to shift. These human resources remain indispensable to the success of any company, but the deployment of a raft of advancing technologies has played an ever-advancing role over time in enabling companies to maximize recoveries and profits.

During the past 50 years, the frequency of recorded natural disasters has surged nearly five-fold. In this blog, I'll be exploring how converging exponential technologies (AI, robotics, drones, sensors, networks) are transforming the future of disaster relief--how we can prevent them in the first place and get help to victims during that first golden hour wherein immediate relief can save lives. When it comes to immediate and high-precision emergency response, data is gold. Already, the meteoric rise of space-based networks, stratosphere-hovering balloons, and 5G telecommunications infrastructure is in the process of connecting every last individual on the planet. Aside from democratizing the world's information, however, this upsurge in connectivity will soon grant anyone the ability to broadcast detailed geo-tagged data, particularly those most vulnerable to natural disasters.

As artificial intelligence systems spread to more diverse and larger tasks in many domains, the machine learning algorithms, and in particular the deep learning models and the databases required to train them are getting bigger themselves. Some algorithms do allow for some scaling of large computations by leveraging data parallelism. However, they often require a large amount of data to be exchanged in order to ensure the shared knowledge throughout the compute nodes is accurate. In this work, the effect of different levels of communications between deep learning models is studied, in particular how it affects performance. The first approach studied looks at decentralizing the numerous computations that are done in parallel in training procedures such as synchronous and asynchronous stochastic gradient descent. In this setting, a simplified communication that consists of exchanging low bandwidth outputs between compute nodes can be beneficial. In the following chapter, the communication protocol is slightly modified to further include training instructions. Indeed, this is studied in a simplified setup where a pre-trained model, analogous to a teacher, can customize a randomly initialized model's training procedure to accelerate learning. Finally, a communication channel where two deep learning models can exchange a purposefully crafted language is explored while allowing for different ways of optimizing that language.

This paper addresses the problem of identifying sparse linear time-invariant (LTI) systems from a single sample trajectory generated by the system dynamics. We introduce a Lasso-like estimator for the parameters of the system, taking into account their sparse nature. Assuming that the system is stable, or that it is equipped with an initial stabilizing controller, we provide sharp finite-time guarantees on the accurate recovery of both the sparsity structure and the parameter values of the system. In particular, we show that the proposed estimator can correctly identify the sparsity pattern of the system matrices with high probability, provided that the length of the sample trajectory exceeds a threshold. Furthermore, we show that this threshold scales polynomially in the number of nonzero elements in the system matrices, but logarithmically in the system dimensions --- this improves on existing sample complexity bounds for the sparse system identification problem. We further extend these results to obtain sharp bounds on the $\ell_{\infty}$-norm of the estimation error and show how different properties of the system---such as its stability level and \textit{mutual incoherency}---affect this bound. Finally, an extensive case study on power systems is presented to illustrate the performance of the proposed estimation method.

These days human beings are facing many environmental challenges due to frequently occurring drought hazards. It may have an effect on the countrys environment, the community, and industries. Several adverse impacts of drought hazard are continued in Pakistan, including other hazards. However, early measurement and detection of drought can provide guidance to water resources management for employing drought mitigation policies. In this paper, we used a multilayer perceptron neural network (MLPNN) algorithm for drought forecasting. We applied and tested MLPNN algorithm on monthly time series data of Standardized Precipitation Evapotranspiration Index (SPEI) for seventeen climatological stations located in Northern Area and KPK (Pakistan). We found that MLPNN has potential capability for SPEI drought forecasting based on performance measures (i.e., Mean Average Error (MAE), the coefficient of correlation R, and Root Mean Square Error (RMSE). Water resources and management planner can take necessary action in advance (e.g., in water scarcity areas) by using MLPNN model as part of their decision making.

In many applications, observed data are influenced by some combination of latent causes. For example, suppose sensors are placed inside a building to record responses such as temperature, humidity, power consumption and noise levels. These random, observed responses are typically affected by many unobserved, latent factors (or features) within the building such as the number of individuals, the turning on and off of electrical devices, power surges, etc. These latent factors are usually present for a contiguous period of time before disappearing; further, multiple factors could be present at a time. This paper develops new probabilistic methodology and inference methods for random object generation influenced by latent features exhibiting temporal persistence. Every datum is associated with subsets of a potentially infinite number of hidden, persistent features that account for temporal dynamics in an observation. The ensuing class of dynamic models constructed by adapting the Indian Buffet Process --- a probability measure on the space of random, unbounded binary matrices --- finds use in a variety of applications arising in operations, signal processing, biomedicine, marketing, image analysis, etc. Illustrations using synthetic and real data are provided.

Material recognition methods use image context and local cues for pixel-wise classification. In many cases only a single image is available to make a material prediction. Image sequences, routinely acquired in applications such as mutliview stereo, can provide a sampling of the underlying reflectance functions that reveal pixel-level material attributes. We investigate multi-view material segmentation using two datasets generated for building material segmentation and scene material segmentation from the SpaceNet Challenge satellite image dataset. In this paper, we explore the impact of multi-angle reflectance information by introducing the \textit{reflectance residual encoding}, which captures both the multi-angle and multispectral information present in our datasets. The residuals are computed by differencing the sparse-sampled reflectance function with a dictionary of pre-defined dense-sampled reflectance functions. Our proposed reflectance residual features improves material segmentation performance when integrated into pixel-wise and semantic segmentation architectures. At test time, predictions from individual segmentations are combined through softmax fusion and refined by building segment voting. We demonstrate robust and accurate pixelwise segmentation results using the proposed material segmentation pipeline.