Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of TinyML, its practical implementation presents unique challenges. This study aims to bridge the gap between prototyping single TinyML models and developing reliable TinyML systems in production: (1) Embedded devices operate in dynamically changing conditions. Existing TinyML solutions primarily focus on inference, with models trained offline on powerful machines and deployed as static objects. However, static models may underperform in the real world due to evolving input data distributions. We propose online learning to enable training on constrained devices, adapting local models towards the latest field conditions. (2) Nevertheless, current on-device learning methods struggle with heterogeneous deployment conditions and the scarcity of labeled data when applied across numerous devices. We introduce federated meta-learning incorporating online learning to enhance model generalization, facilitating rapid learning. This approach ensures optimal performance among distributed devices by knowledge sharing. (3) Moreover, TinyML's pivotal advantage is widespread adoption. Embedded devices and TinyML models prioritize extreme efficiency, leading to diverse characteristics ranging from memory and sensors to model architectures. Given their diversity and non-standardized representations, managing these resources becomes challenging as TinyML systems scale up. We present semantic management for the joint management of models and devices at scale. We demonstrate our methods through a basic regression example and then assess them in three real-world TinyML applications: handwritten character image classification, keyword audio classification, and smart building presence detection, confirming our approaches' effectiveness.

We study the problem of incentive-compatible online learning with bandit feedback. In this class of problems, the experts are self-interested agents who might misrepresent their preferences with the goal of being selected most often. The goal is to devise algorithms which are simultaneously incentive-compatible, that is the experts are incentivised to report their true preferences, and have no regret with respect to the preferences of the best fixed expert in hindsight. \citet{freeman2020no} propose an algorithm in the full information setting with optimal $O(\sqrt{T \log(K)})$ regret and $O(T^{2/3}(K\log(K))^{1/3})$ regret in the bandit setting. In this work we propose the first incentive-compatible algorithms that enjoy $O(\sqrt{KT})$ regret bounds. We further demonstrate how simple loss-biasing allows the algorithm proposed in Freeman et al. 2020 to enjoy $\tilde O(\sqrt{KT})$ regret. As a byproduct of our approach we obtain the first bandit algorithm with nearly optimal regret bounds in the adversarial setting which works entirely on the observed loss sequence without the need for importance-weighted estimators. Finally, we provide an incentive-compatible algorithm that enjoys asymptotically optimal best-of-both-worlds regret guarantees, i.e., logarithmic regret in the stochastic regime as well as worst-case $O(\sqrt{KT})$ regret.

Considering learner engagement has a mutual benefit for both learners and instructors. Instructors can help learners increase their attention, involvement, motivation, and interest. On the other hand, instructors can improve their instructional performance by evaluating the cumulative results of all learners and upgrading their training programs. This paper proposes a general, lightweight model for selecting and processing features to detect learners' engagement levels while preserving the sequential temporal relationship over time. During training and testing, we analyzed the videos from the publicly available DAiSEE dataset to capture the dynamic essence of learner engagement. We have also proposed an adaptation policy to find new labels that utilize the affective states of this dataset related to education, thereby improving the models' judgment. The suggested model achieves an accuracy of 68.57\% in a specific implementation and outperforms the studied state-of-the-art models detecting learners' engagement levels.

In this paper, we present a comprehensive survey of the metaverse, envisioned as a transformative dimension of next-generation Internet technologies. This study not only outlines the structural components of our survey but also makes a substantial scientific contribution by elucidating the foundational concepts underlying the emergence of the metaverse. We analyze its architecture by defining key characteristics and requirements, thereby illuminating the nascent reality set to revolutionize digital interactions. Our analysis emphasizes the importance of collaborative efforts in developing metaverse standards, thereby fostering a unified understanding among industry stakeholders, organizations, and regulatory bodies. We extend our scrutiny to critical technologies integral to the metaverse, including interactive experiences, communication technologies, ubiquitous computing, digital twins, artificial intelligence, and cybersecurity measures. For each technological domain, we rigorously assess current contributions, principal techniques, and representative use cases, providing a nuanced perspective on their potential impacts. Furthermore, we delve into the metaverse's diverse applications across education, healthcare, business, social interactions, industrial sectors, defense, and mission-critical operations, highlighting its extensive utility. Each application is thoroughly analyzed, demonstrating its value and addressing associated challenges. The survey concludes with an overview of persistent challenges and future directions, offering insights into essential considerations and strategies necessary to harness the full potential of the metaverse. Through this detailed investigation, our goal is to articulate the scientific contributions of this survey paper, transcending a mere structural overview to highlight the transformative implications of the metaverse.

We study an online learning problem in general-sum Stackelberg games, where players act in a decentralized and strategic manner. We study two settings depending on the type of information for the follower: (1) the limited information setting where the follower only observes its own reward, and (2) the side information setting where the follower has extra side information about the leader's reward. We show that for the follower, myopically best responding to the leader's action is the best strategy for the limited information setting, but not necessarily so for the side information setting -- the follower can manipulate the leader's reward signals with strategic actions, and hence induce the leader's strategy to converge to an equilibrium that is better off for itself. Based on these insights, we study decentralized online learning for both players in the two settings. Our main contribution is to derive last-iterate convergence and sample complexity results in both settings. Notably, we design a new manipulation strategy for the follower in the latter setting, and show that it has an intrinsic advantage against the best response strategy. Our theories are also supported by empirical results.

Analytical models developed in offline settings with pre-prepared data are typically used to predict students' performance. However, when data are available over time, this learning method is not suitable anymore. Online learning is increasingly used to update the online models from stream data. A rehearsal technique is typically used, which entails re-training the model on a small training set that is updated each time new data is received. The main challenge in this regard is the construction of the training set with appropriate data samples to maintain good model performance. Typically, a random selection of samples is made, which can deteriorate the model's performance. In this paper, we propose a memory-based online incremental learning approach for updating an online classifier that predicts student performance using stream data. The approach is based on the use of the genetic algorithm heuristic while respecting the memory space constraints as well as the balance of class labels. In contrast to random selection, our approach improves the stability of the analytical model by promoting diversity when creating the training set. As a proof of concept, we applied it to the open dataset OULAD. Our approach achieves a notable improvement in model accuracy, with an enhancement of nearly 10% compared to the current state-of-the-art, while maintaining a relatively low standard deviation in accuracy, ranging from 1% to 2.1%.

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is pessimistic regret analysis results in the sense that although the cost function can change from one episode to the next, the evolution in many settings is not adversarial. To address this, we introduce and study a new variant of AMDP, which aims to minimize regret while utilizing a set of cost predictors. For this setting, we develop a new policy search method that achieves a sublinear optimistic regret with high probability, that is a regret bound which gracefully degrades with the estimation power of the cost predictors. Establishing such optimistic regret bounds is nontrivial given that (i) as we demonstrate, the existing importance-weighted cost estimators cannot establish optimistic bounds, and (ii) the feedback model of AMDP is different (and more realistic) than the existing optimistic online learning works. Our result, in particular, hinges upon developing a novel optimistically biased cost estimator that leverages cost predictors and enables a high-probability regret analysis without imposing restrictive assumptions. We further discuss practical extensions of the proposed scheme and demonstrate its efficacy numerically.

Every few years, an emerging technology shows up at the doorstep of schools and universities promising to transform education. Technologies and apps that include or are powered by generative artificial intelligence, also known as GenAI. These technologies are sold on the potential they hold for education. For example, Khan Academy's founder opened his 2023 Ted Talk by arguing that "we're at the cusp of using AI for probably the biggest positive transformation that education has ever seen." As optimistic as these visions of the future may be, the realities of educational technology over the past few decades have not lived up to their promises.

Google announced Friday that it is releasing a course aimed at teaching one million Americans how to use artificial intelligence tools. As part of the rollout, the tech giant also announced that its charitable arm, Google.org, The new AI skills course will be available for 49 on Coursera, a for-profit online course provider. The announcement comes after Google scrapped its rules requiring suppliers and staffing firms it works with to provide good pay and benefits to their employees - along with laying off thousands of employees despite turning record profits. Google announced two new initiatives: One is a self-paced course on AI skills, the other is a grant program for AI job skills training.

Online learning has soared in popularity in the educational landscape of COVID-19 and carries the benefits of increased flexibility and access to far-away training resources. However, it also restricts communication between peers and teachers, limits physical interactions and confines learning to the computer screen and keyboard. In this project, we designed a novel way to engage students in collaborative online learning by using haptic-enabled tangible robots, Cellulo. We built a library which connects two robots remotely for a learning activity based around the structure of a biological cell. To discover how separate modes of haptic feedback might differentially affect collaboration, two modes of haptic force-feedback were implemented (haptic co-location and haptic consensus). With a case study, we found that the haptic co-location mode seemed to stimulate collectivist behaviour to a greater extent than the haptic consensus mode, which was associated with individualism and less interaction. While the haptic co-location mode seemed to encourage information pooling, participants using the haptic consensus mode tended to focus more on technical co-ordination. This work introduces a novel system that can provide interesting insights on how to integrate haptic feedback into collaborative remote learning activities in future.