Many real-world applications can be modelled as complex networks, and such networks include the Internet, epidemic disease networks, transport networks, power grids, protein-folding structures and others. Network integrity and robustness are important to ensure that crucial networks are protected and undesired harmful networks can be dismantled. Network structure and integrity can be controlled by a set of key nodes, and to find the optimal combination of nodes in a network to ensure network structure and integrity can be an NP-complete problem. Despite extensive studies, existing methods have many limitations and there are still many unresolved problems. This paper presents a probabilistic approach based on neighborhood information and node importance, namely, neighborhood information-based probabilistic algorithm (NIPA). We also define a new centrality-based importance measure (IM), which combines the contribution ratios of the neighbor nodes of each target node and two-hop node information. Our proposed NIPA has been tested for different network benchmarks and compared with three other methods: optimal attack strategy (OAS), high betweenness first (HBF) and high degree first (HDF). Experiments suggest that the proposed NIPA is most effective among all four methods. In general, NIPA can identify the most crucial node combination with higher effectiveness, and the set of optimal key nodes found by our proposed NIPA is much smaller than that by heuristic centrality prediction. In addition, many previously neglected weakly connected nodes are identified, which become a crucial part of the newly identified optimal nodes. Thus, revised strategies for protection are recommended to ensure the safeguard of network integrity. Further key issues and future research topics are also discussed.

Researchers have discovered a solid-state material mimics the neural signals responsible for transmitting information in the human brain. The work is a step toward developing circuitry that functions like the human brain--neuromorphic computing. The researchers discovered a neuron-like electrical switching mechanism in the solid-state material β'-CuxV2O5--specifically, how it reversibly morphs between conducting and insulating behavior on command. The team was able to clarify the underlying mechanism driving this behavior by taking a new look at β'-CuxV2O5, a remarkable chameleon-like material that changes with temperature or an applied electrical stimulus. In the process, they zeroed in on how copper ions move around inside the material and how this subtle dance in turn sloshes electrons around to transform it.

In order to help with an array of challenges facing the digitization of the energy industry, companies, governments and regulatory agencies are looking at ways to make our energy consumption more efficient. One of the key sustainable and reliable solutions is the introduction of the smart grid, which uses a variety of operation and energy measures including smart meters, smart appliances, renewable energy resources and energy efficient resources to provide more data for energy operators, powering better decision-making and resource usage. The vast amount of data captured from operations, whether that be asset performance data, customer data, advanced metering data or geographic information, only continues to grow. Smart grids continuously collect and synthesize huge amounts of data from millions of smart sensors to make timely decisions on how best to allocate energy resources. AI in the energy sector is helping to empower the smart power grid, providing more effective and more profitable power trading and better regulation of power consumption.

We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model directly from a micro-scale description. Polymer solution is used as an example to demonstrate the essential ideas. To faithfully retain molecular fidelity, we establish a micro-macro correspondence via a set of encoders for the micro-scale polymer configurations and their macro-scale counterparts, a set of nonlinear conformation tensors. The dynamics of these conformation tensors can be derived from the micro-scale model and the relevant terms can be parametrized using machine learning. The final model, named the deep non-Newtonian model (DeePN$^2$), takes the form of conventional non-Newtonian fluid dynamics models, with a new form of the objective tensor derivative. Numerical results demonstrate the accuracy of DeePN$^2$.

Scientists estimate that up to 90pc of the carbon emissions from industrial use of fossil fuels could be captured in this way, although the practice requires a continued supply of suitable locations to store the captured carbon. The researchers from MIT caution that their algorithm is only as effective as the data which it has been fed. They plan to give it even more data in the future to train it to better analyse seismic waves. Laurent Demanet, a professor of applied mathematics and one of the authors of the paper, told MIT News: "Using this neural network will help us find the missing frequencies to ultimately improve the subsurface image and find the composition of the Earth." MIT's research was funded by petroleum refining business Total SA and the US Air Force.

Phoenix Air Unmanned, LLC (PAU) is seeking information on the availability of Unmanned Aircraft Systems to support linear infrastructure inspections. The UAS will be operated by PAU who has been contracted by Xcel Energy as their unmanned flight service provider and they plan to purchase a minimum of 4 aircraft initially with the possibility of additional aircraft in the future. Xcel Energy, Inc. owns over 120,000 miles of transmission and distribution infrastructure across eight states (CO, MI, MN, NM, WI, ND, SD, TX) that must be inspected at regular intervals as required by state and federal regulations. Xcel Energy, Inc. is a utility holding company with a service company (Xcel Energy Services) and four wholly owned utility subsidiaries that serve electric and natural gas customers. PAU was established in 2014 for commercial UAS operations.

Phoenix Air Unmanned, LLC (PAU) is seeking information on the availability of Unmanned Aircraft Systems to support linear infrastructure inspections. The UAS will be operated by PAU who has been contracted by Xcel Energy as their unmanned flight service provider and they plan to purchase a minimum of 4 aircraft initially with the possibility of additional aircraft in the future. Xcel Energy, Inc. owns over 120,000 miles of transmission and distribution infrastructure across eight states (CO, MI, MN, NM, WI, ND, SD, TX) that must be inspected at regular intervals as required by state and federal regulations. Xcel Energy, Inc. is a utility holding company with a service company (Xcel Energy Services) and four wholly owned utility subsidiaries that serve electric and natural gas customers. PAU was established in 2014 for commercial UAS operations.

Throughout each industrial era, the companies best able to embrace change have become the most likely to succeed. In The Future Computed: AI and Manufacturing, Microsoft Senior Director Greg Shaw explores how AI, automation and the internet of things (IoT) present new challenges and opportunities. Here are some of the manufacturers already demonstrating how the latest tech advances are changing the way they work. A collaboration between Thyssenkrupp and Microsoft has led to the development of the elevator industry's first real-time, cloud-based predictive maintenance system. This means an elevator can accurately predict when it is about to fail and summon an engineer, making it far less likely that people could get trapped inside.

Graph neural networks have recently achieved great successes in predicting quantum mechanical properties of molecules. These models represent a molecule as a graph using only the distance between atoms (nodes). They do not, however, consider the spatial direction from one atom to another, despite directional information playing a central role in empirical potentials for molecules, e.g. in angular potentials. To alleviate this limitation we propose directional message passing, in which we embed the messages passed between atoms instead of the atoms themselves. Each message is associated with a direction in coordinate space. These directional message embeddings are rotationally equivariant since the associated directions rotate with the molecule. We propose a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them. Additionally, we use spherical Bessel functions and spherical harmonics to construct theoretically well-founded, orthogonal representations that achieve better performance than the currently prevalent Gaussian radial basis representations while using fewer than 1/4 of the parameters. We leverage these innovations to construct the directional message passing neural network (DimeNet). DimeNet outperforms previous GNNs on average by 76% on MD17 and by 31% on QM9. Our implementation is available online.

Approximate inference in probability models is a fundamental task in machine learning. Approximate inference provides powerful tools to Bayesian reasoning, decision making, and Bayesian deep learning. The main goal is to estimate the expectation of interested functions w.r.t. a target distribution. When it comes to high dimensional probability models and large datasets, efficient approximate inference becomes critically important. In this thesis, we propose a new framework for approximate inference, which combines the advantages of these three frameworks and overcomes their limitations. Our proposed four algorithms are motivated by the recent computational progress of Stein's method. Our proposed algorithms are applied to continuous and discrete distributions under the setting when the gradient information of the target distribution is available or unavailable. Theoretical analysis is provided to prove the convergence of our proposed algorithms. Our adaptive IS algorithm iteratively improves the importance proposal by functionally decreasing the KL divergence between the updated proposal and the target. When the gradient of the target is unavailable, our proposed sampling algorithm leverages the gradient of a surrogate model and corrects induced bias with importance weights, which significantly outperforms other gradient-free sampling algorithms. In addition, our theoretical results enable us to perform the goodness-of-fit test on discrete distributions. At the end of the thesis, we propose an importance-weighted method to efficiently aggregate local models in distributed learning with one-shot communication. Results on simulated and real datasets indicate the statistical efficiency and wide applicability of our algorithm.