Since the inception of Industry 4.0 in 2012, emerging technologies have enabled the acquisition of vast amounts of data from diverse sources such as machine tools, robust and affordable sensor systems with advanced information models, and other sources within Smart Manufacturing Systems (SMS). As a result, the amount of data that is available in manufacturing settings has exploded, allowing data-hungry tools such as Artificial Intelligence (AI) and Machine Learning (ML) to be leveraged. Time-series analytics has been successfully applied in a variety of industries, and that success is now being migrated to pattern recognition applications in manufacturing to support higher quality products, zero defect manufacturing, and improved customer satisfaction. However, the diverse landscape of manufacturing presents a challenge for successfully solving problems in industry using time-series pattern recognition. The resulting research gap of understanding and applying the subject matter of time-series pattern recognition in manufacturing is a major limiting factor for adoption in industry. The purpose of this paper is to provide a structured perspective of the current state of time-series pattern recognition in manufacturing with a problem-solving focus. By using an ontology to classify and define concepts, how they are structured, their properties, the relationships between them, and considerations when applying them, this paper aims to provide practical and actionable guidelines for application and recommendations for advancing time-series analytics.

In statistics, the least absolute shrinkage and selection operator (Lasso) is a regression method that performs both variable selection and regularization. There is a lot of literature available, discussing the statistical properties of the regression coefficients estimated by the Lasso method. However, there lacks a comprehensive review discussing the algorithms to solve the optimization problem in Lasso. In this review, we summarize five representative algorithms to optimize the objective function in Lasso, including the iterative shrinkage threshold algorithm (ISTA), fast iterative shrinkage-thresholding algorithms (FISTA), coordinate gradient descent algorithm (CGDA), smooth L1 algorithm (SLA), and path following algorithm (PFA). Additionally, we also compare their convergence rate, as well as their potential strengths and weakness.

Medical devices and artificial intelligence systems rapidly transform healthcare provisions. At the same time, due to their nature, AI in or as medical devices might get exposed to cyberattacks, leading to patient safety and security risks. This book chapter is divided into three parts. The first part starts by setting the scene where we explain the role of cybersecurity in healthcare. Then, we briefly define what we refer to when we talk about AI that is considered a medical device by itself or supports one. To illustrate the risks such medical devices pose, we provide three examples: the poisoning of datasets, social engineering, and data or source code extraction. In the second part, the paper provides an overview of the European Union's regulatory framework relevant for ensuring the cybersecurity of AI as or in medical devices (MDR, NIS Directive, Cybersecurity Act, GDPR, the AI Act proposal and the NIS 2 Directive proposal). Finally, the third part of the paper examines possible challenges stemming from the EU regulatory framework. In particular, we look toward the challenges deriving from the two legislative proposals and their interaction with the existing legislation concerning AI medical devices' cybersecurity. They are structured as answers to the following questions: (1) how will the AI Act interact with the MDR regarding the cybersecurity and safety requirements?; (2) how should we interpret incident notification requirements from the NIS 2 Directive proposal and MDR?; and (3) what are the consequences of the evolving term of critical infrastructures? [This is a draft chapter. The final version will be available in Research Handbook on Health, AI and the Law edited by Barry Solaiman & I. Glenn Cohen, forthcoming 2023, Edward Elgar Publishing Ltd]

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any distribution of test examples. Current ML systems can fail silently on test examples with distribution shifts. In order to improve reliability of ML models due to covariate or domain shift, we propose algorithms that enable models to: (a) generalize to a larger family of test distributions, (b) evaluate accuracy under distribution shifts, (c) adapt to a target distribution. We study causes of impaired robustness to domain shifts and present algorithms for training domain robust models. A key source of model brittleness is due to domain overfitting, which our new training algorithms suppress and instead encourage domain-general hypotheses. While we improve robustness over standard training methods for certain problem settings, performance of ML systems can still vary drastically with domain shifts. It is crucial for developers and stakeholders to understand model vulnerabilities and operational ranges of input, which could be assessed on the fly during the deployment, albeit at a great cost. Instead, we advocate for proactively estimating accuracy surfaces over any combination of prespecified and interpretable domain shifts for performance forecasting. We present a label-efficient estimation to address estimation over a combinatorial space of domain shifts. Further, when a model's performance on a target domain is found to be poor, traditional approaches adapt the model using the target domain's resources. Standard adaptation methods assume access to sufficient labeled resources, which may be impractical for deployed models. We initiate a study of lightweight adaptation techniques with only unlabeled data resources with a focus on language applications.

With the development of computer-assisted techniques, research communities including biochemistry and deep learning have been devoted into the drug discovery field for over a decade. Various applications of deep learning have drawn great attention in drug discovery, such as molecule generation, molecular property prediction, retrosynthesis prediction, and reaction prediction. While most existing surveys only focus on one of the applications, limiting the view of researchers in the community. In this paper, we present a comprehensive review on the aforementioned four aspects, and discuss the relationships among different applications. The latest literature and classical benchmarks are presented for better understanding the development of variety of approaches. We commence by summarizing the molecule representation format in these works, followed by an introduction of recent proposed approaches for each of the four tasks. Furthermore, we review a variety of commonly used datasets and evaluation metrics and compare the performance of deep learning-based models. Finally, we conclude by identifying remaining challenges and discussing the future trend for deep learning methods in drug discovery.

With the recent advances in hardware and rendering techniques, 3D models have emerged everywhere in our life. Yet creating 3D shapes is arduous and requires significant professional knowledge. Meanwhile, Deep learning has enabled high-quality 3D shape reconstruction from various sources, making it a viable approach to acquiring 3D shapes with minimal effort. Importantly, to be used in common 3D applications, the reconstructed shapes need to be represented as polygonal meshes, which is a challenge for neural networks due to the irregularity of mesh tessellations. In this survey, we provide a comprehensive review of mesh reconstruction methods that are powered by machine learning. We first describe various representations for 3D shapes in the deep learning context. Then we review the development of 3D mesh reconstruction methods from voxels, point clouds, single images, and multi-view images. Finally, we identify several challenges in this field and propose potential future directions.

Federated learning (FL) is a promising technique for addressing the rising privacy and security issues. Its main ingredient is to cooperatively learn the model among the distributed clients without uploading any sensitive data. In this paper, we conducted a thorough review of the related works, following the development context and deeply mining the key technologies behind FL from both theoretical and practical perspectives. Specifically, we first classify the existing works in FL architecture based on the network topology of FL systems with detailed analysis and summarization. Next, we abstract the current application problems, summarize the general techniques and frame the application problems into the general paradigm of FL base models. Moreover, we provide our proposed solutions for model training via FL. We have summarized and analyzed the existing FedOpt algorithms, and deeply revealed the algorithmic development principles of many first-order algorithms in depth, proposing a more generalized algorithm design framework. Based on these frameworks, we have instantiated FedOpt algorithms. As privacy and security is the fundamental requirement in FL, we provide the existing attack scenarios and the defense methods. To the best of our knowledge, we are among the first tier to review the theoretical methodology and propose our strategies since there are very few works surveying the theoretical approaches. Our survey targets motivating the development of high-performance, privacy-preserving, and secure methods to integrate FL into real-world applications.

Recent advancements in AI have coincided with ever-increasing efforts in the research community to investigate, classify and evaluate various methods aimed at making AI models explainable. However, most of existing attempts present a method-centric view of eXplainable AI (XAI) which is typically meaningful only for domain experts. There is an apparent lack of a robust qualitative and quantitative performance framework that evaluates the suitability of explanations for different types of users. We survey relevant efforts, and then, propose a unified, inclusive and user-centred taxonomy for XAI based on the principles of General System's Theory, which serves us as a basis for evaluating the appropriateness of XAI approaches for all user types, including both developers and end users.

As a data engineer, you will design and maintain data platform road maps and data structures that support business and technology objectives. Naturally inquisitive and open to the deep exploration of underlying data, finding actionable insights, and working with functional competencies to drive identified actions. You also enjoy working both freely and as part of a team and have the confidence to influence and communicate with stakeholders at all levels, and to work in a fast-paced complex environment with conflicting priorities. Reporting into the delivery leader, you will deliver consumable, contemporary, and immediate data content to support and drive business decisions. The key focus of the role is to deliver a custom solution to support various business critical requirements.

The development of ChatGPT began in 2021 when OpenAI researchers first introduced the GPT-3 language model. This model, which is based on a neural network architecture, was designed to generate human-like text based on a given prompt or input. The success of GPT-3 led to the development of ChatGPT, which was specifically designed to enable more natural and human-like communication between humans and machines. Since its development, ChatGPT has been used in a wide range of IT applications, including chatbots, customer service agents, and automated content generation. Its ability to generate accurate and contextually appropriate responses to natural language inputs has made it a valuable tool for companies looking to streamline and automate their IT processes. Overall, ChatGPT is a revolutionary technology that is changing the way we think about artificial intelligence and human-machine communication. Its impact on the IT industry is sure to be felt for years to come.