The Li-ion battery is a complex physicochemical system that generally takes applied current as input and terminal voltage as output. The mappings from current to voltage can be described by several kinds of models, such as accurate but inefficient physics-based models, and efficient but sometimes inaccurate equivalent circuit and black-box models. To realize accuracy and efficiency simultaneously in battery modeling, we propose to build a data-driven surrogate for a battery system while incorporating the underlying physics as constraints. In this work, we innovatively treat the functional mapping from current curve to terminal voltage as a composite of operators, which is approximated by the powerful deep operator network (DeepONet). Its learning capability is firstly verified through a predictive test for Li-ion concentration at two electrodes. In this experiment, the physics-informed DeepONet is found to be more robust than the purely data-driven DeepONet, especially in temporal extrapolation scenarios. A composite surrogate is then constructed for mapping current curve and solid diffusivity to terminal voltage with three operator networks, in which two parallel physics-informed DeepONets are firstly used to predict Li-ion concentration at two electrodes, and then based on their surface values, a DeepONet is built to give terminal voltage predictions. Since the surrogate is differentiable anywhere, it is endowed with the ability to learn from data directly, which was validated by using terminal voltage measurements to estimate input parameters. The proposed surrogate built upon operator networks possesses great potential to be applied in on-board scenarios, such as battery management system, since it integrates efficiency and accuracy by incorporating underlying physics, and also leaves an interface for model refinement through a totally differentiable model structure.

Avenues to mitigate the main issue, the von Neumann bottleneck, include in-memory and near-memory architectures, as well as algorithmic approaches. Here we leverage the low-power and the inherently binary operation of magnetic tunnel junctions (MTJs) to demonstrate neural network hardware inference based on passive arrays of MTJs. In general, transferring a trained network model to hardware for inference is confronted by degradation in performance due to device-todevice variations, write errors, parasitic resistance, and nonidealities in the substrate. To quantify the effect of these hardware realities, we benchmark 300 unique weight matrix solutions of a 2-layer perceptron to classify the Wine dataset for both classification accuracy and write fidelity. Despite device imperfections, we achieve software-equivalent accuracy of up to 95.3 % with proper tuning of network parameters in 15 15 MTJ arrays having a range of device sizes. The success of this tuning process shows that new metrics are needed to characterize the performance and quality of networks reproduced in mixed signal hardware. I. INTRODUCTION Over the past decade, artificial intelligence algorithms have achieved human-level performance on increasingly complex tasks at the cost of increased neural network size, computing resources, and energy consumption [1-5]. OpenAI's GPT-3, for example, a state-ot-the-art natural language processor, contains 175 billion parameters and requires 3.14 10 Running these algorithms for inference applications--applications that require the model to make predictions but not learn new information--requires lesser but still overwhelming amounts of energy. This energy inefficiency is in part due to implementing these algorithms using general-purpose hardware such as central and graphical processing units (CPUs and GPUs). Because CPUs and GPUs have traditional von Neumann computing architectures, they do not store data in the same spatial location as where computation is carried out. For this reason, energy is consumed in moving the data, and the speed of computation is throttled by the time it takes to shuttle from the storage to the computation location. This so-called von Neumann bottleneck has been shown to be severe on large neural network models, with studies showing the majority of the network time and energy can be expended distributing gradient and model data [11-13]. Algorithmic approaches to lessening the data bottleneck have focused on simplifying neural network models to achieve equivalent accuracy with less memory overhead.

The new method, developed by a team led by Imperial College London researchers, could slash the energy cost of artificial intelligence (AI), which is currently doubling globally every 3.5 months. In a paper published today in Nature Nanotechnology, the international team have produced the first proof that networks of nanomagnets can be used to perform AI-like processing. The researchers showed nanomagnets can be used for'time-series prediction' tasks, such as predicting and regulating insulin levels in diabetic patients. Artificial intelligence that uses'neural networks' aims to replicate the way parts of the brain work, where neurons talk to each other to process and retain information. A lot of the maths used to power neural networks was originally invented by physicists to describe the way magnets interact, but at the time it was too difficult to use magnets directly as researchers didn't know how to put data in and get information out.

Though techno-thriller The Circle (2017) is more a comment on the ethical implications of social networks than the practicalities of external video analytics, the improbably tiny'SeeChange' camera at the center of the plot is what truly pushes the movie into the'science-fiction' category. A wireless and free-roaming device about the size of a large marble, it's not the lack of solar panels or the inefficiency of drawing power from other ambient sources (such as radio waves) that makes SeeChange an unlikely prospect, but the fact that it's going to have to compress video 24/7, on whatever scant charge it's able to maintain. Powering cheap sensors of this type is a core area of research in computer vision (CV) and video analytics, particularly in non-urban environments where the sensor will have to eke out the maximum performance from very limited power resources (batteries, solar, etc.). In cases where such an edge IoT/CV device of this type must send image content to a central server (often through conventional cell coverage networks), the choices are hard: either the device needs to run some kind of lightweight neural network locally in order to send only optimized segments of relevant data for server side processing; or it has to send'dumb' video for the plugged-in cloud resources to evaluate. Though motion-activation through event-based Smart Vision Sensors (SVS) can cut down this overhead, that activation monitoring also costs energy.

We learn new skills by repetition and reinforcement learning. Through trial and error, we repeat actions leading to good outcomes, try to avoid bad outcomes and seek to improve those in between. Researchers are now designing algorithms based on a form of artificial intelligence that uses reinforcement learning. They are applying them to automate chemical synthesis, drug discovery and even play games like chess and Go. Scientists at the U.S. Department of Energy's (DOE) Argonne National Laboratory have developed a reinforcement learning algorithm for yet another application.

Environmental impacts are far reaching, the effects of climate change devastating, and organizations are striving to shape their business in a way that is environmentally sustainable and equipped to thrive in the future. Ronald van Loon is a Huawei partner, and discussed green solutions at Huawei's Global Analyst Summit in Shenzhen China, where Huawei highlighted the importance of building a green intelligent world for 2030. The intelligent world in 2030 will emphasize low carbon living, virtual tourism and classrooms, buildings that consume lower energy, electric and intelligent vehicles, virtual factories, better ways for businesses and people to collaborate in real-time, and more renewable energy solutions will go mainstream. Huawei released a report called "Green Development 2030" that focuses on how green development will change people's lives and industries. According to Huawei, "by 2030, we expect 80% of energy to come from renewable sources and energy efficiency to increase 100 times."

In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to detecting anomalies from streams of multivariate time series data is of significant importance. Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned normal representations can empower anomaly detection as the model has learned to capture certain key underlying data regularities. A typical formulation is to learn a predictive model, i.e., use a window of time series data to predict future data values. In this paper, we propose an alternative self-supervised learning task. By randomly masking a portion of the inputs and training a model to estimate them using the remaining ones, MAD is an improvement over the traditional left-to-right next step prediction (NSP) task. Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.

One of the first steps in many text-based social science studies is to retrieve documents that are relevant for the analysis from large corpora of otherwise irrelevant documents. The conventional approach in social science to address this retrieval task is to apply a set of keywords and to consider those documents to be relevant that contain at least one of the keywords. But the application of incomplete keyword lists risks drawing biased inferences. More complex and costly methods such as query expansion techniques, topic model-based classification rules, and active as well as passive supervised learning could have the potential to more accurately separate relevant from irrelevant documents and thereby reduce the potential size of bias. Yet, whether applying these more expensive approaches increases retrieval performance compared to keyword lists at all, and if so, by how much, is unclear as a comparison of these approaches is lacking. This study closes this gap by comparing these methods across three retrieval tasks associated with a data set of German tweets (Linder, 2017), the Social Bias Inference Corpus (SBIC) (Sap et al., 2020), and the Reuters-21578 corpus (Lewis, 1997). Results show that query expansion techniques and topic model-based classification rules in most studied settings tend to decrease rather than increase retrieval performance. Active supervised learning, however, if applied on a not too small set of labeled training instances (e.g.

Non-smooth optimization is a core ingredient of many imaging or machine learning pipelines. Non-smoothness encodes structural constraints on the solutions, such as sparsity, group sparsity, low-rank and sharp edges. It is also the basis for the definition of robust loss functions and scale-free functionals such as square-root Lasso. Standard approaches to deal with non-smoothness leverage either proximal splitting or coordinate descent. These approaches are effective but usually require parameter tuning, preconditioning or some sort of support pruning. In this work, we advocate and study a different route, which operates a non-convex but smooth over-parametrization of the underlying non-smooth optimization problems. This generalizes quadratic variational forms that are at the heart of the popular Iterative Reweighted Least Squares (IRLS). Our main theoretical contribution connects gradient descent on this reformulation to a mirror descent flow with a varying Hessian metric. This analysis is crucial to derive convergence bounds that are dimension-free. This explains the efficiency of the method when using small grid sizes in imaging. Our main algorithmic contribution is to apply the Variable Projection (VarPro) method which defines a new formulation by explicitly minimizing over part of the variables. This leads to a better conditioning of the minimized functional and improves the convergence of simple but very efficient gradient-based methods, for instance quasi-Newton solvers. We exemplify the use of this new solver for the resolution of regularized regression problems for inverse problems and supervised learning, including total variation prior and non-convex regularizers.

The datasets I worked with were a combination of publically-available information on weather and load for regions covered by ISO New England, the corporation responsible for distributing energy across the 6 New England states. I used hourly data from October 2018 to present, which at the time of this project constituted 3 years of data. Since the regions controlled by ISO-NE were likely to have different energy demands due to each area's specific geographical attributes, I decided to simplify the problem by honing in on only one of the 8 regions. I selected the Connecticut ISO zone. The challenge at hand was to see if I could accurately forecast one-hour-ahead load for the Connecticut ISO zone given past values of the features I had available.