Machine learning models that are developed to be invariant under certain types of data transformations have shown improved generalization in practice. However, a principled understanding of why invariance benefits generalization is limited. Given a dataset, there is often no principled way to select "suitable" data transformations under which model invariance guarantees better generalization. This paper studies the generalization benefit of model invariance by introducing the sample cover induced by transformations, i.e., a representative subset of a dataset that can approximately recover the whole dataset using transformations. For any data transformations, we provide refined generalization bounds for invariant models based on the sample cover. We also characterize the "suitability" of a set of data transformations by the sample covering number induced by transformations, i.e., the smallest size of its induced sample covers. We show that we may tighten the generalization bounds for "suitable" transformations that have a small sample covering number. In addition, our proposed sample covering number can be empirically evaluated and thus provides a guidance for selecting transformations to develop model invariance for better generalization. In experiments on multiple datasets, we evaluate sample covering numbers for some commonly used transformations and show that the smaller sample covering number for a set of transformations (e.g., the 3D-view transformation) indicates a smaller gap between the test and training error for invariant models, which verifies our propositions.

Europe was hit by several, disastrous heat and drought events in recent summers. Besides thermodynamic influences, such hot and dry extremes are driven by certain atmospheric situations including anticyclonic conditions. Effects of climate change on atmospheric circulations are complex and many open research questions remain in this context, e.g., on future trends of anticyclonic conditions. Based on the combination of a catalog of labeled circulation patterns and spatial atmospheric variables, we propose a smoothed convolutional neural network classifier for six types of anticyclonic circulations that are associated with drought and heat. Our work can help to identify important drivers of hot and dry extremes in climate simulations, which allows to unveil the impact of climate change on these drivers. We address various challenges inherent to circulation pattern classification that are also present in other climate patterns, e.g., subjective labels and unambiguous transition periods.

Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set, and subsequently making predictions on a testing data set (i.e., generalizing). In this work, we provide a comprehensive study of generalization performance in QML after training on a limited number $N$ of training data points. We show that the generalization error of a quantum machine learning model with $T$ trainable gates scales at worst as $\sqrt{T/N}$. When only $K \ll T$ gates have undergone substantial change in the optimization process, we prove that the generalization error improves to $\sqrt{K / N}$. Our results imply that the compiling of unitaries into a polynomial number of native gates, a crucial application for the quantum computing industry that typically uses exponential-size training data, can be sped up significantly. We also show that classification of quantum states across a phase transition with a quantum convolutional neural network requires only a very small training data set. Other potential applications include learning quantum error correcting codes or quantum dynamical simulation. Our work injects new hope into the field of QML, as good generalization is guaranteed from few training data.

Recent deep learning research based on Transformer model architectures has demonstrated state-of-the-art performance across a variety of domains and tasks, mostly within the computer vision and natural language processing domains. While some recent studies have implemented Transformers for clinical tasks using electronic health records data, they are limited in scope, flexibility, and comprehensiveness. In this study, we propose a flexible Transformer-based EHR embedding pipeline and predictive model framework that introduces several novel modifications of existing workflows that capitalize on data attributes unique to the healthcare domain. We showcase the feasibility of our flexible design in a case study in the intensive care unit, where our models accurately predict seven clinical outcomes pertaining to readmission and patient mortality over multiple future time horizons.

Artificial intelligence (AI) systems have become increasingly popular in many areas. Nevertheless, AI technologies are still in their developing stages, and many issues need to be addressed. Among those, the reliability of AI systems needs to be demonstrated so that the AI systems can be used with confidence by the general public. In this paper, we provide statistical perspectives on the reliability of AI systems. Different from other considerations, the reliability of AI systems focuses on the time dimension. That is, the system can perform its designed functionality for the intended period. We introduce a so-called SMART statistical framework for AI reliability research, which includes five components: Structure of the system, Metrics of reliability, Analysis of failure causes, Reliability assessment, and Test planning. We review traditional methods in reliability data analysis and software reliability, and discuss how those existing methods can be transformed for reliability modeling and assessment of AI systems. We also describe recent developments in modeling and analysis of AI reliability and outline statistical research challenges in this area, including out-of-distribution detection, the effect of the training set, adversarial attacks, model accuracy, and uncertainty quantification, and discuss how those topics can be related to AI reliability, with illustrative examples. Finally, we discuss data collection and test planning for AI reliability assessment and how to improve system designs for higher AI reliability. The paper closes with some concluding remarks.

The proposed European Artificial Intelligence Act (AIA) is the first attempt to elaborate a general legal framework for AI carried out by any major global economy. As such, the AIA is likely to become a point of reference in the larger discourse on how AI systems can (and should) be regulated. In this article, we describe and discuss the two primary enforcement mechanisms proposed in the AIA: the conformity assessments that providers of high-risk AI systems are expected to conduct, and the post-market monitoring plans that providers must establish to document the performance of high-risk AI systems throughout their lifetimes. We argue that AIA can be interpreted as a proposal to establish a Europe-wide ecosystem for conducting AI auditing, albeit in other words. Our analysis offers two main contributions. First, by describing the enforcement mechanisms included in the AIA in terminology borrowed from existing literature on AI auditing, we help providers of AI systems understand how they can prove adherence to the requirements set out in the AIA in practice. Second, by examining the AIA from an auditing perspective, we seek to provide transferable lessons from previous research about how to refine further the regulatory approach outlined in the AIA. We conclude by highlighting seven aspects of the AIA where amendments (or simply clarifications) would be helpful. These include, above all, the need to translate vague concepts into verifiable criteria and to strengthen the institutional safeguards concerning conformity assessments based on internal checks.

It was actually my first time attending such online event with a Role Play Game-style meeting space. It's my first time using Gather Town to attend a public lecture organized by ICITDA x Universitas Islam Indonesia. He was bringing up a topic of "Cyber Security, Data Science, and Artificial Intelligence". An interesting topic in today's interconnected digital world where there are no such thing as physical boundaries and space. The outline of this topic consisted of the introduction, cybersecurity, data science, artificial intelligence, and the summary.

GoGuardian is a software company that makes, essentially, spyware: software that helps teachers and schools block and monitor what kids are doing online. When a student is using a school-issued Chromebook that has GoGuardian on it, the teacher can see just about everything they're doing. These technologies have been embraced by teachers and state Departments of Education alike, but students are less enthralled with having their online lives constantly surveilled. On Friday's episode of What Next: TBD, I spoke with Priya Anand, a tech reporter for Bloomberg who wrote a story on GoGuardian, about the rise of the school surveillance state and the implications of this technology for student's mental health and privacy. Lizzie O'Leary: You wrote for Bloomberg about Pekin Community High School in Illinois, which has been using GoGuardian for three years.

Pittsburgh Mayor Bill Peduto presented keys to the city to Carnegie Mellon University's Red Whittaker and Andrew Moore on Friday, calling the two "leaders of the fourth industrial revolution." Peduto, who will leave office at the end of the year after serving two terms as mayor and a career in city hall, said it has been an honor to work with Whittaker and Moore throughout much of the 2000s as Pittsburgh emerged as a hotbed of tech talent and grew its economy around robotics, autonomy, computer science, machine learning and artificial intelligence. The mayor described Whittaker and Moore as humble men who love Pittsburgh and chose to stay in the city to train top-level scientists and develop transformative technologies. They created new industries that not only changed Pittsburgh but changed the world," Peduto said. "They changed Pittsburgh beyond its economy and brought it back to the world stage."

Ever since disruptive technologies like artificial intelligence, robotics, machine learning, etc. made their debut in modern society, the world has turned upside down. Today, everything starting from the way we wake up by alarms and the automatic option that turns off the light when we go to sleep are powered by technology. Even though many disruptive technologies might also emerge in the future, some of the moments of history and some of the'firsts' have a remarkable spot in human minds. They carry the scientists' hard work and passion to deliver a futuristic solution to humankind. To celebrate their efforts, Analytics Insight has listed remarkable moments of disruptive technologies that were photographed.