Strong foundations in basic AI techniques are key to understanding more advanced concepts. We believe that introducing AI techniques, such as search methods, early in higher education helps create a deeper understanding of the concepts seen later in more advanced AI and algorithms courses. We present a project-based and competition-based bachelor course that gives second-year students an introduction to search methods applied to board games. In groups of two, students have to use network programming and AI methods to build an AI agent to compete in a board game tournament-othello was this year's game. Students are evaluated based on the quality of their projects and on their performance during the final tournament. We believe that the introduction of gamification, in the form of competition-based learning, allows for a better learning experience for the students.

Several solutions This is a tutorial paper on Recurrent Neural Network were proposed for this issue, some of which are close-toidentity (RNN), Long Short-Term Memory Network weight matrix (Mikolov et al., 2015), long delays (LSTM), and their variants. We start with a (Lin et al., 1995), leaky units (Jaeger et al., 2007; Sutskever dynamical system and backpropagation through & Hinton, 2010), and echo state networks (Jaeger & Haas, time for RNN. Then, we discuss the problems 2004; Jaeger, 2007). of gradient vanishing and explosion in longterm dependencies. We explain close-to-identity Sequence modeling requires both short-term and long-term weight matrix, long delays, leaky units, and echo dependencies. For example, consider the sentence "The state networks for solving this problem. Then, police is chasing the thief".

Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), which partitions an ER buffer into Event Tables, each capturing important subsequences of optimal behavior. We prove a theoretical advantage over the traditional monolithic buffer approach and combine SSET with an existing prioritized sampling strategy to further improve learning speed and stability. Empirical results in challenging MiniGrid domains, benchmark RL environments, and a high-fidelity car racing simulator demonstrate the advantages and versatility of SSET over existing ER buffer sampling approaches.

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual information to infer masked image regions. We believe that this context aggregation ability is particularly essential to the medical image domain where each anatomical structure is functionally and mechanically connected to other structures and regions. Because there is no ImageNet-scale medical image dataset for pre-training, we investigate a self pre-training paradigm with MAE for medical image analysis tasks. Our method pre-trains a ViT on the training set of the target data instead of another dataset. Thus, self pre-training can benefit more scenarios where pre-training data is hard to acquire. Our experimental results show that MAE self pre-training markedly improves diverse medical image tasks including chest X-ray disease classification, abdominal CT multi-organ segmentation, and MRI brain tumor segmentation. Code is available at https://github.com/cvlab-stonybrook/SelfMedMAE

Fresh fears have been raised about the training material used for some of the largest and most powerful artificial intelligence models, after several investigations exposed the fascist, pirated and malicious sources from which the data is harvested. One such dataset is the Colossal Clean Crawled Corpus, or C4, assembled by Google from more than 15m websites and used to train both the search engine's LaMDA AI as well as Meta's GPT competitor, LLaMA. The dataset is public, but its scale has made it difficult to examine the contents: it is supposedly a "clean" version of a more expansive dataset, Common Crawl, with "noisy" content, offensive language and racist slurs removed from the material. But an investigation by the Washington Post reveals that C4's "cleanliness" is only skin deep. While it draws on websites such as the Guardian – which makes up 0.05% of the entire dataset - and Wikipedia, as well as large databases such as Google Patents and the scientific journal hub PLOS, it also contains less reputable sites. The white nationalist site VDARE is in the database, one of the 1,000 largest sites, as is the far-right news site Breitbart.

In recent years, advancements in artificial intelligence (AI) have led to the development of large language models like GPT-4, demonstrating potential applications in various fields, including education. This study investigates the feasibility and effectiveness of using ChatGPT, a GPT-4 based model, in achieving satisfactory performance on the Fundamentals of Engineering (FE) Environmental Exam. This study further shows a significant improvement in the model's accuracy when answering FE exam questions through noninvasive prompt modifications, substantiating the utility of prompt modification as a viable approach to enhance AI performance in educational contexts. Furthermore, the findings reflect remarkable improvements in mathematical capabilities across successive iterations of ChatGPT models, showcasing their potential in solving complex engineering problems. Our paper also explores future research directions, emphasizing the importance of addressing AI challenges in education, enhancing accessibility and inclusion for diverse student populations, and developing AI-resistant exam questions to maintain examination integrity. By evaluating the performance of ChatGPT in the context of the FE Environmental Exam, this study contributes valuable insights into the potential applications and limitations of large language models in educational settings. As AI continues to evolve, these findings offer a foundation for further research into the responsible and effective integration of AI models across various disciplines, ultimately optimizing the learning experience and improving student outcomes.

Robotic manipulation is currently undergoing a profound paradigm shift due to the increasing needs for flexible manufacturing systems, and at the same time, because of the advances in enabling technologies such as sensing, learning, optimization, and hardware. This demands for robots that can observe and reason about their workspace, and that are skillfull enough to complete various assembly processes in weakly-structured settings. Moreover, it remains a great challenge to enable operators for teaching robots on-site, while managing the inherent complexity of perception, control, motion planning and reaction to unexpected situations. Motivated by real-world industrial applications, this paper demonstrates the potential of such a paradigm shift in robotics on the industrial case of an e-Bike motor assembly. The paper presents a concept for teaching and programming adaptive robots on-site and demonstrates their potential for the named applications. The framework includes: (i) a method to teach perception systems onsite in a self-supervised manner, (ii) a general representation of object-centric motion skills and force-sensitive assembly skills, both learned from demonstration, (iii) a sequencing approach that exploits a human-designed plan to perform complex tasks, and (iv) a system solution for adapting and optimizing skills online. The aforementioned components are interfaced through a four-layer software architecture that makes our framework a tangible industrial technology. To demonstrate the generality of the proposed framework, we provide, in addition to the motivating e-Bike motor assembly, a further case study on dense box packing for logistics automation.

Technological development continues to advance, with consequences for the use of robots in health care. For this reason, this workshop contribution aims at consideration of how socially assistive robots can be integrated into care and what tasks they can take on. This also touches on the degree of autonomy of these robots and the balance of decision support and decision making in different situations. We want to show that decision making by robots is mediated by the balance between autonomy and safety. Our results are based on Design Fiction and Zine-Making workshops we conducted with scientific experts. Ultimately, we show that robots' actions take place in social groups. A robot does not typically decide alone, but its decision-making is embedded in group processes. The concept of heteromation, which describes the interconnection of human and machine actions, offers fruitful possibilities for exploring how robots can be integrated into caring relationships.

Data-driven approaches coupled with physical knowledge are powerful techniques to model systems. The goal of such models is to efficiently solve for the underlying field by combining measurements with known physical laws. As many systems contain unknown elements, such as missing parameters, noisy data, or incomplete physical laws, this is widely approached as an uncertainty quantification problem. The common techniques to handle all the variables typically depend on the numerical scheme used to approximate the posterior, and it is desirable to have a method which is independent of any such discretization. Information field theory (IFT) provides the tools necessary to perform statistics over fields that are not necessarily Gaussian. We extend IFT to physics-informed IFT (PIFT) by encoding the functional priors with information about the physical laws which describe the field. The posteriors derived from this PIFT remain independent of any numerical scheme and can capture multiple modes, allowing for the solution of problems which are ill-posed. We demonstrate our approach through an analytical example involving the Klein-Gordon equation. We then develop a variant of stochastic gradient Langevin dynamics to draw samples from the joint posterior over the field and model parameters. We apply our method to numerical examples with various degrees of model-form error and to inverse problems involving nonlinear differential equations. As an addendum, the method is equipped with a metric which allows the posterior to automatically quantify model-form uncertainty. Because of this, our numerical experiments show that the method remains robust to even an incorrect representation of the physics given sufficient data. We numerically demonstrate that the method correctly identifies when the physics cannot be trusted, in which case it automatically treats learning the field as a regression problem.

This paper introduces a new learning-based approach for approximately solving the Kidney-Exchange Problem (KEP), an NP-hard problem on graphs. The problem consists of, given a pool of kidney donors and patients waiting for kidney donations, optimally selecting a set of donations to optimize the quantity and quality of transplants performed while respecting a set of constraints about the arrangement of these donations. The proposed technique consists of two main steps: the first is a Graph Neural Network (GNN) trained without supervision; the second is a deterministic non-learned search heuristic that uses the output of the GNN to find paths and cycles. To allow for comparisons, we also implemented and tested an exact solution method using integer programming, two greedy search heuristics without the machine learning module, and the GNN alone without a heuristic. We analyze and compare the methods and conclude that the learning-based two-stage approach is the best solution quality, outputting approximate solutions on average 1.1 times more valuable than the ones from the deterministic heuristic alone.