The null space of the $k$-th order Laplacian $\mathbf{\mathcal L}_k$, known as the {\em $k$-th homology vector space}, encodes the non-trivial topology of a manifold or a network. Understanding the structure of the homology embedding can thus disclose geometric or topological information from the data. The study of the null space embedding of the graph Laplacian $\mathbf{\mathcal L}_0$ has spurred new research and applications, such as spectral clustering algorithms with theoretical guarantees and estimators of the Stochastic Block Model. In this work, we investigate the geometry of the $k$-th homology embedding and focus on cases reminiscent of spectral clustering. Namely, we analyze the {\em connected sum} of manifolds as a perturbation to the direct sum of their homology embeddings. We propose an algorithm to factorize the homology embedding into subspaces corresponding to a manifold's simplest topological components. The proposed framework is applied to the {\em shortest homologous loop detection} problem, a problem known to be NP-hard in general. Our spectral loop detection algorithm scales better than existing methods and is effective on diverse data such as point clouds and images.

Blend two or three metals together and you get an alloy that usually looks and acts like a metal, with its atoms arranged in rigid geometric patterns. But once in a while, under just the right conditions, you get something entirely new: a futuristic alloy called metallic glass that's amorphous, with its atoms arranged every which way, much like the atoms of the glass in a window. Its glassy nature makes it stronger and lighter than today's best steel, plus it stands up better to corrosion and wear. Even though metallic glass shows a lot of promise as a protective coating and alternative to steel, only a few thousand of the millions of possible combinations of ingredients have been evaluated over the past 50 years, and only a handful developed to the point that they may become useful. Now a group led by scientists at the Department of Energy's SLAC National Accelerator Laboratory, the National Institute of Standards and Technology (NIST) and Northwestern University has reported a shortcut for discovering and improving metallic glass -- and, by extension, other elusive materials -- at a fraction of the time and cost.

In the production work of the future, autonomous systems will support people through data-based analyzes and intelligent solution patterns for value-adding activities. Experts from the two Fraunhofer institutes IPA and IAO in Stuttgart will show their guests at the "International Open Lab Day" on April 16, 2021 the benefits that artificial intelligence (AI) can bring. In the future, AI could identify potential for optimization, make fitters' work easier or set up personnel deployment plans: These are just a few examples of how AI can help make production more resilient and flexible. However, this does not mean that the human being becomes an assistant to the algorithms, but remains the director of the processes, works efficiently in an adaptive environment and no longer has to take on so many control tasks. Digital technologies help to make production work more human-centered.

A new way of using machine learning to examine satellite images could help people around the world. More than 700 imaging satellites orbit the earth, but only governments and companies with wealth and expertise can access the data they produce. Now, researchers said in a recent paper that they have invented a machine learning system using low-cost, easy-to-use technology that could bring satellite analytical power to researchers and governments worldwide. "To plan infrastructure like roads and bridges or to target food aid, we need to know where people live and what their needs are," Jonathan Proctor, a co-author of the paper, told Lifewire in an email interview. "Satellite imagery and machine learning can help measure socio-economic conditions in places where other measurements are insufficient."

They have the sort of names that only teenage boys or aspiring Bond villains would dream up (REvil, Grief, Wizard Spider, Ragnar), they base themselves in countries that do not cooperate with international law enforcement and they don't care whether they attack a hospital or a multinational corporation. Ransomware gangs are suddenly everywhere, seemingly unstoppable – and very successful. In June, meat producer JBS, which supplies over a fifth of all the beef in the US, paid a £7.8m ransom to regain access to its computer systems. The same month, the US's largest national fuel pipeline, Colonial Pipeline, paid £3.1m to ransomware hackers after they locked the company's systems, causing days of fuel shortages and paralysing the east coast. "It was the hardest decision I've made in my 39 years in the energy industry," said a deflated-looking Colonial CEO Joseph Blount in an evidence session before Congress. In July, hackers attacked software firm Kaseya, demanding £50m.

To build challenging multi-hop question answering datasets, we propose a bottom-up semi-automatic process of constructing multi-hop question via composition of single-hop questions. Constructing multi-hop questions as composition of single-hop questions allows us to exercise greater control over the quality of the resulting multi-hop questions. This process allows building a dataset with (i) connected reasoning where each step needs the answer from a previous step; (ii) minimal train-test leakage by eliminating even partial overlap of reasoning steps; (iii) variable number of hops and composition structures; and (iv) contrasting unanswerable questions by modifying the context. We use this process to construct a new multihop QA dataset: MuSiQue-Ans with ~25K 2-4 hop questions using seed questions from 5 existing single-hop datasets. Our experiments demonstrate that MuSique is challenging for state-of-the-art QA models (e.g., human-machine gap of $~$30 F1 pts), significantly harder than existing datasets (2x human-machine gap), and substantially less cheatable (e.g., a single-hop model is worse by 30 F1 pts). We also build an even more challenging dataset, MuSiQue-Full, consisting of answerable and unanswerable contrast question pairs, where model performance drops further by 13+ F1 pts. For data and code, see \url{https://github.com/stonybrooknlp/musique}.

Energy disaggregation, also known as non-intrusive load monitoring (NILM), challenges the problem of separating the whole-home electricity usage into appliance-specific individual consumptions, which is a typical application of data analysis. {NILM aims to help households understand how the energy is used and consequently tell them how to effectively manage the energy, thus allowing energy efficiency which is considered as one of the twin pillars of sustainable energy policy (i.e., energy efficiency and renewable energy).} Although NILM is unidentifiable, it is widely believed that the NILM problem can be addressed by data science. Most of the existing approaches address the energy disaggregation problem by conventional techniques such as sparse coding, non-negative matrix factorization, and hidden Markov model. Recent advances reveal that deep neural networks (DNNs) can get favorable performance for NILM since DNNs can inherently learn the discriminative signatures of the different appliances. In this paper, we propose a novel method named adversarial energy disaggregation (AED) based on DNNs. We introduce the idea of adversarial learning into NILM, which is new for the energy disaggregation task. Our method trains a generator and multiple discriminators via an adversarial fashion. The proposed method not only learns shard representations for different appliances, but captures the specific multimode structures of each appliance. Extensive experiments on real-world datasets verify that our method can achieve new state-of-the-art performance.

In this paper, the design of a rational decision support system (RDSS) for a connected and autonomous vehicle charging infrastructure (CAV-CI) is studied. In the considered CAV-CI, the distribution system operator (DSO) deploys electric vehicle supply equipment (EVSE) to provide an EV charging facility for human-driven connected vehicles (CVs) and autonomous vehicles (AVs). The charging request by the human-driven EV becomes irrational when it demands more energy and charging period than its actual need. Therefore, the scheduling policy of each EVSE must be adaptively accumulated the irrational charging request to satisfy the charging demand of both CVs and AVs. To tackle this, we formulate an RDSS problem for the DSO, where the objective is to maximize the charging capacity utilization by satisfying the laxity risk of the DSO. Thus, we devise a rational reward maximization problem to adapt the irrational behavior by CVs in a data-informed manner. We propose a novel risk adversarial multi-agent learning system (RAMALS) for CAV-CI to solve the formulated RDSS problem. In RAMALS, the DSO acts as a centralized risk adversarial agent (RAA) for informing the laxity risk to each EVSE. Subsequently, each EVSE plays the role of a self-learner agent to adaptively schedule its own EV sessions by coping advice from RAA. Experiment results show that the proposed RAMALS affords around 46.6% improvement in charging rate, about 28.6% improvement in the EVSE's active charging time and at least 33.3% more energy utilization, as compared to a currently deployed ACN EVSE system, and other baselines.

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train detection models without assuming the examples illustrating all possible classes of anomaly. Specifically, the proposed approach learns discriminative normality (regularity) by leveraging the labeled anomalies and a prior probability to enforce expressive representations of normality and unbounded deviated representations of abnormality. This is achieved by an end-to-end optimization of anomaly scores with a neural deviation learning, in which the anomaly scores of normal samples are imposed to approximate scalar scores drawn from the prior while that of anomaly examples is enforced to have statistically significant deviations from these sampled scores in the upper tail. Furthermore, our model is optimized to learn fine-grained normality and abnormality by top-K multiple-instance-learning-based feature subspace deviation learning, allowing more generalized representations. Comprehensive experiments on nine real-world image anomaly detection benchmarks show that our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings. Our model can also offer explanation capability as a result of its prior-driven anomaly score learning. Code and datasets are available at: https://git.io/DevNet.

A special issue of Geophysical Prospecting is being planned on machine learning applications in geophysical exploration and monitoring. Artificial intelligence, and in particular its subdomain machine learning, has revolutionized many science and engineering disciplines during the past decade. In many domains such as image recognition, machine translation, and speech analysis, machine learning outperforms conventional techniques and has emerged as the method of choice. It is no surprise that recently geophysicists have also found great value in machine learning to automate workflows, extract valuable information from big data, and create new pathways in solving challenging computational problems. Despite this surge in interest, we are still in the early days of developing machine learning applications for subsurface resource exploration, and the geophysical community at large will benefit from a better understanding of the promise of machine learning in transforming industrial practices.