The effective integration of generative artificial intelligence in education is a fundamental aspect to prepare future generations. This study proposes an accelerated learning methodology in artificial intelligence, focused on its generative capacity, as a way to achieve this goal. It recognizes the challenge of getting teachers to engage with new technologies and adapt their methods in all subjects, not just those related to AI. This methodology not only promotes interest in science, technology, engineering and mathematics, but also facilitates student understanding of the ethical uses and risks associated with AI. Students' perceptions of generative AI are examined, addressing their emotions towards its evolution, evaluation of its ethical implications, and everyday use of AI tools. In addition, AI applications commonly used by students and their integration into other disciplines are investigated. The study aims to provide educators with a deeper understanding of students' perceptions of AI and its relevance in society and in their future career paths.

In online bilateral trade, a platform posts prices to incoming pairs of buyers and sellers that have private valuations for a certain good. If the price is lower than the buyers' valuation and higher than the sellers' valuation, then a trade takes place. Previous work focused on the platform perspective, with the goal of setting prices maximizing the gain from trade (the sum of sellers' and buyers' utilities). Gain from trade is, however, potentially unfair to traders, as they may receive highly uneven shares of the total utility. In this work we enforce fairness by rewarding the platform with the fair gain from trade, defined as the minimum between sellers' and buyers' utilities. After showing that any no-regret learning algorithm designed to maximize the sum of the utilities may fail badly with fair gain from trade, we present our main contribution: a complete characterization of the regret regimes for fair gain from trade when, after each interaction, the platform only learns whether each trader accepted the current price. Specifically, we prove the following regret bounds: $\Theta(\ln T)$ in the deterministic setting, $\Omega(T)$ in the stochastic setting, and $\tilde{\Theta}(T^{2/3})$ in the stochastic setting when sellers' and buyers' valuations are independent of each other. We conclude by providing tight regret bounds when, after each interaction, the platform is allowed to observe the true traders' valuations.

The performance of Automatic Speech Recognition (ASR) systems has constantly increased in state-of-the-art development. However, performance tends to decrease considerably in more challenging conditions (e.g., background noise, multiple speaker social conversations) and with more atypical speakers (e.g., children, non-native speakers or people with speech disorders), which signifies that general improvements do not necessarily transfer to applications that rely on ASR, e.g., educational software for younger students or language learners. In this study, we focus on the gap in performance between recognition results for native and non-native, read and spontaneous, Swedish utterances transcribed by different ASR services. We compare the recognition results using Word Error Rate and analyze the linguistic factors that may generate the observed transcription errors.

Most of the dominant approaches to continual learning are based on either memory replay, parameter isolation, or regularization techniques that require task boundaries to calculate task statistics. We propose a static architecture-based method that doesn't use any of these. We show that we can improve the continual learning performance by replacing the final layer of our networks with our pairwise interaction layer. The pairwise interaction layer uses sparse representations from a Winner-take-all style activation function to find the relevant correlations in the hidden layer representations. The networks using this architecture show competitive performance in MNIST and FashionMNIST-based continual image classification experiments. We demonstrate this in an online streaming continual learning setup where the learning system cannot access task labels or boundaries.

In control problems for insect-scale direct-drive experimental platforms under tandem wing influence, the precision and safety of control during plug-and-play online training and control processes are paramount. The primary challenge facing existing reinforcement learning models is their limited safety in the exploration process and the stability of the continuous training process. Addressing these challenges, we introduce the ConcertoRL algorithm to enhance control precision and stabilize the online training process, which consists of two main innovations: a time-interleaved mechanism to interweave classical controllers with reinforcement learning-based controllers aiming to improve control precision in the initial stages, a policy composer organizes the experience gained from previous learning to ensure the stability of the online training process. This paper conducts a series of experiments. First, experiments incorporating the time-interleaved mechanism demonstrate a substantial performance boost of approximately 70% over scenarios without reinforcement learning enhancements and a 50% increase in efficiency compared to reference controllers with doubled control frequencies. These results highlight the algorithm's ability to create a synergistic effect that exceeds the sum of its parts. Second, Ablation studies on the policy composer further reveal that this module significantly enhances the stability of ConcertoRL during online training. Lastly, experiments on the universality of the current ConcertoRL algorithm framework demonstrate its compatibility with various classical controllers, consistently achieving excellent control outcomes. ConcertoRL sets a new benchmark in control effectiveness for challenges posed by direct-drive platforms under tandem wing influence and establishes a comprehensive framework for integrating classical and reinforcement learning-based control methodologies.

Exploiting the power of pre-trained models, prompt-based approaches stand out compared to other continual learning solutions in effectively preventing catastrophic forgetting, even with very few learnable parameters and without the need for a memory buffer. While existing prompt-based continual learning methods excel in leveraging prompts for state-of-the-art performance, they often lack a theoretical explanation for the effectiveness of prompting. This paper conducts a theoretical analysis to unravel how prompts bestow such advantages in continual learning, thus offering a new perspective on prompt design. We first show that the attention block of pre-trained models like Vision Transformers inherently encodes a special mixture of experts architecture, characterized by linear experts and quadratic gating score functions. This realization drives us to provide a novel view on prefix tuning, reframing it as the addition of new task-specific experts, thereby inspiring the design of a novel gating mechanism termed Non-linear Residual Gates (NoRGa). Through the incorporation of non-linear activation and residual connection, NoRGa enhances continual learning performance while preserving parameter efficiency. The effectiveness of NoRGa is substantiated both theoretically and empirically across diverse benchmarks and pretraining paradigms.

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, without any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to fine-tuning. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward model to provide feedback for on-policy sampling responses. Recently, offline methods that directly fit responses with binary preferences in the dataset have emerged as alternatives. However, existing methods do not explicitly model preference strength information, which is crucial for distinguishing different response pairs. To overcome this limitation, we propose Online Self-Preferring (OSP) language models to learn from self-generated response pairs and self-judged preference strengths. For each prompt and corresponding self-generated responses, we introduce a ranked pairing method to construct multiple response pairs with preference strength information. We then propose the soft-preference cross-entropy loss to leverage such information. Empirically, we demonstrate that leveraging preference strength is crucial for avoiding overfitting and enhancing alignment performance. OSP achieves state-of-the-art alignment performance across various metrics in two widely used human preference datasets. OSP is parameter-efficient and more robust than the dominant online method, RLHF when limited offline data are available and generalizing to out-of-domain tasks. Moreover, OSP language models established by LLMs with proficiency in self-preferring can efficiently self-improve without external supervision.

Organizational decision-making is crucial for success, yet cognitive biases can significantly affect risk preferences, leading to suboptimal outcomes. Risk seeking preferences for losses, driven by biases such as loss aversion, pose challenges and can result in severe negative consequences, including financial losses. This research introduces the ABI approach, a novel solution designed to support organizational decision-makers by automatically identifying and explaining risk seeking preferences during decision-making. This research makes a novel contribution by automating the identification and explanation of risk seeking preferences using Cumulative Prospect theory (CPT) from Behavioral Economics. The ABI approach transforms theoretical insights into actionable, real-time guidance, making them accessible to a broader range of organizations and decision-makers without requiring specialized personnel. By contextualizing CPT concepts into business language, the approach facilitates widespread adoption and enhances decision-making processes with deep behavioral insights. Our systematic literature review identified significant gaps in existing methods, especially the lack of automated solutions with a concrete mechanism for automatically identifying risk seeking preferences, and the absence of formal knowledge representation, such as ontologies, for identifying and explaining the risk preferences. The ABI Approach addresses these gaps, offering a significant contribution to decision-making research and practice. Furthermore, it enables automatic collection of historical decision data with risk preferences, providing valuable insights for enhancing strategic management and long-term organizational performance. An experiment provided preliminary evidence on its effectiveness in helping decision-makers recognize their risk seeking preferences during decision-making in the loss domain.

Gradient based optimization algorithms deployed in Machine Learning (ML) applications are often analyzed and compared by their convergence rates or regret bounds. While these rates and bounds convey valuable information they don't always directly translate to stability guarantees. Stability and similar concepts, like robustness, will become ever more important as we move towards deploying models in real-time and safety critical systems. In this work we build upon the results in Gaudio et al. 2021 and Moreu and Annaswamy 2022 for second order gradient descent when applied to explicitly time varying cost functions and provide more general stability guarantees. These more general results can aid in the design and certification of these optimization schemes so as to help ensure safe and reliable deployment for real-time learning applications. We also hope that the techniques provided here will stimulate and cross-fertilize the analysis that occurs on the same algorithms from the online learning and stochastic optimization communities.