In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with both states and actions represented through a feature vector. The underlying structure of the environments allows the transition dynamics to be factored into two components: one that is environment-specific and another that is shared. Consider a set of environments that share the laws of motion as an example. In this setting, the agent can take a finite amount of reward-free interactions from a subset of these environments. The agent then must be able to approximately solve any planning task defined over any environment in the original set, relying on the above interactions only. Can we design a provably efficient algorithm that achieves this ambitious goal of systematic generalization? In this paper, we give a partially positive answer to this question. First, we provide a tractable formulation of systematic generalization by employing a causal viewpoint. Then, under specific structural assumptions, we provide a simple learning algorithm that guarantees any desired planning error up to an unavoidable sub-optimality term, while showcasing a polynomial sample complexity.

The popularity of generative text AI tools in answering questions has led to concerns regarding their potential negative impact on students' academic performance and the challenges that educators face in evaluating student learning. To address these concerns, this paper introduces an evolutionary approach that aims to identify the best set of Bloom's taxonomy keywords to generate questions that these tools have low confidence in answering. The effectiveness of this approach is evaluated through a case study that uses questions from a Data Structures and Representation course being taught at the University of New South Wales in Canberra, Australia. The results demonstrate that the optimization algorithm is able to find keywords from different cognitive levels to create questions that ChatGPT has low confidence in answering. This study is a step forward to offer valuable insights for educators seeking to create more effective questions that promote critical thinking among students.

Selective experience replay is a popular strategy for integrating lifelong learning with deep reinforcement learning. Selective experience replay aims to recount selected experiences from previous tasks to avoid catastrophic forgetting. Furthermore, selective experience replay based techniques are model agnostic and allow experiences to be shared across different models. However, storing experiences from all previous tasks make lifelong learning using selective experience replay computationally very expensive and impractical as the number of tasks increase. To that end, we propose a reward distribution-preserving coreset compression technique for compressing experience replay buffers stored for selective experience replay. We evaluated the coreset compression technique on the brain tumor segmentation (BRATS) dataset for the task of ventricle localization and on the whole-body MRI for localization of left knee cap, left kidney, right trochanter, left lung, and spleen. The coreset lifelong learning models trained on a sequence of 10 different brain MR imaging environments demonstrated excellent performance localizing the ventricle with a mean pixel error distance of 12.93 for the compression ratio of 10x. In comparison, the conventional lifelong learning model localized the ventricle with a mean pixel distance of 10.87. Similarly, the coreset lifelong learning models trained on whole-body MRI demonstrated no significant difference (p=0.28) between the 10x compressed coreset lifelong learning models and conventional lifelong learning models for all the landmarks. The mean pixel distance for the 10x compressed models across all the landmarks was 25.30, compared to 19.24 for the conventional lifelong learning models. Our results demonstrate that the potential of the coreset-based ERB compression method for compressing experiences without a significant drop in performance.

The generalized equation (also called the [non]linear inclusion) provides a unified template to model various problems in computational mathematics and related fields su ch as the optimality condition of optimization problems (in both unconstrained and constrained settings), minimax optimization, variational inequality, complementarity, two-person game, and fixed-point problem s, see, e.g., [11, 24, 50, 112, 116, 118, 120]. Theory and numerical methods for this equation and its special case s have been extensively studied for many decades, see, e.g., the following monographs and the references quot ed therein [11, 50, 94, 119]. At the same time, several applications of this mathematical tool in operatio ns research, economics, uncertainty quantification, and transportations have been investigated [14, 52, 61, 50, 72]. In the last few years, there has been a surge of research in minimax problems due to new applications in mach ine learning and robust optimization, especially in generative adversarial networks (GANs), adversarial tr aining, and distributionally robust optimization, see, e.g., [4, 14, 55, 76, 84, 114] as a few examples. Minimax probl ems have also found new applications in online learning and reinforcement learning, among many others, se e, e.g., [4, 9, 15, 55, 67, 76, 78, 84, 114, 139]. Such prominent applications have motivated the research in minimax optimization and variational inequality problems (VIPs). On the one hand, classical algorithms such as gradient descent-ascent, extragradient, and primal-dual methods have been revisited, improved, and ext ended. On the other hand, new variants such as accelerated extragradient and accelerated operator split ting schemes have also been developed and equipped with rigorous convergence guarantees and practical perfor mance evaluation. This new development motivates us to write this survey paper, with the focus on sublinear con vergence rate analysis.

Fox News correspondent Matt Finn has the latest on the impact of AI technology that some say could outpace humans on'Special Report.' WASHINGTON – While most people look to artificial intelligence, or AI, for quick answers to complex problems, a growing number of school districts are turning to the technology to keep their students and staff safe. A school district in Charles County, Maryland, roughly an hour from Washington D.C., is in the process of installing software and hardware which would allow their current security cameras to detect a potential active shooter. "This artificial intelligence has the ability to be able to identify a weapon, to assess what's going on and how that person is acting," said Jason Stoddard, Director of School safety and Security for Charles County Public Schools. The district, through a state grant, is in the process of installing AI gun detection technology at all of its campuses.

Note: The Coursera courses mentioned in the blog can be audited for free, meaning that you have access to all the course content without any cost. Programming is an essential part of your data science journey. If you know how to code in R, Python, or Julia, it will be quite easy for you to translate algorithms into functions. Moreover, you will learn better techniques to create a program or data reports. I will highly recommend you start with Python and learn the basic syntax and advanced functionalities.

Graduate students at the University of Tokyo have created a group of futuristic-looking drone prototypes that can change their structural shape mid-air. Graduate students at the University of Tokyo have outdone themselves and are changing the way we look at drones with their newest invention. They created a group of futuristic-looking drone prototypes that can change their structural shape midair. As you will see in the video below, this could be a game changer if the drones were to be used by companies or the military for moving and transporting things. CLICK TO GET KURT'S CYBERGUY NEWSLETTER WITH QUICK TIPS, TECH REVIEWS, SECURITY ALERTS AND EASY HOW-TO'S TO MAKE YOU SMARTER The students were inspired by the idea of a dragon flying through the air, as we've seen in movies like "Game of Thrones," and how they can twist and turn their bodies as they fly.

Note: The Coursera courses mentioned in the blog can be audited for free, meaning that you have access to all the course content and can read and view it without any cost. Machine learning is the backbone of modern technology. Almost every big company in the world is trying to use it to get the most out of the data. By taking the free courses, you will learn about classification, regression, clustering, and reinforcement learning. Moreover, you will learn about feature engineering, advanced algorithms, and optimizing techniques.

Pupils should be made to do some of their coursework'in class under direct supervision', exam boards have said - amid fears students are cheating their way through school. Recently, breakthroughs in artificial intelligence such as ChatGPT have led to concerns that young people may use them to achieve higher grades. The program is able to create writing and other content – such as coursework or essays - almost indistinguishable from that of a human. The Joint Council for Qualifications (JCQ), which represents the UK's major exam boards, has published guidance for teachers and assessors on'protecting the integrity of qualifications' in the context of AI use. Schools should make pupils aware of the risks of using AI and the possible consequences of using it'inappropriately' in assessment, the guidance said.

The HBO show is a prequel to Game of Thrones, and that series ended so badly I don't want anything more to do with that fictional world. But maybe A.I. could change my mind? At South by Southwest earlier this month, Greg Brockman, president of OpenAI, the company that created ChatGPT, said, "Imagine if you could ask your A.I. to make a new ending that goes in a different way." Could A.I. be the solution to fixing every novel and script someone has a problem with--customizing revisions to make them shorter or longer, less or more violent, more or less "woke"? Even if A.I. could make changes to movies and books that you personally find dissatisfying, part of those works' value lies in the shared conversations they inspire--conversations that require opinions about common, historically situated texts.