Apostolis Zarras, Athanasia Kollarou, Aristeidis Farao
et al.
The rising adoption of artificial intelligence and machine learning in critical sectors underscores the pressing need for robust systems capable of withstanding adversarial threats. While deep learning architectures have revolutionized tasks such as image recognition, their susceptibility to adversarial techniques remains an open challenge. This article evaluates the impact of various adversarial methods, including the fast gradient sign method, projected gradient descent, DeepFool, and Carlini & Wagner, on five neural network models: a fully connected neural network, LeNet, Simple convolutional neural network (CNN), MobileNetV2, and VGG11. Using the E V AI SION tool explicitly developed for this research, these attacks were implemented and analyzed based on accuracy, F1-score, and misclassification rate. The results revealed varying levels of vulnerability across the tested models, with simpler architectures occasionally outperforming more complex ones. These findings emphasize the importance of selecting the most appropriate adversarial technique for a given architecture and customizing the associated attack parameters to achieve optimal results in each scenario.
Wali Khan Monib, Atika Qazi, Rosyzie Anna Apong
et al.
Generative AI (Gen AI), exemplified by ChatGPT, has witnessed a remarkable surge in popularity recently. This cutting-edge technology demonstrates an exceptional ability to produce human-like responses and engage in natural language conversations guided by context-appropriate prompts. However, its integration into education has become a subject of ongoing debate. This review examines the challenges of using Gen AI like ChatGPT in education and offers effective strategies. To retrieve relevant literature, a search of reputable databases was conducted, resulting in the inclusion of twenty-two publications. Using Atlas.ti, the analysis reflected six primary challenges with plagiarism as the most prevalent issue, closely followed by responsibility and accountability challenges. Concerns were also raised about privacy, data protection, safety, and security risks, as well as discrimination and bias. Additionally, there were challenges about the loss of soft skills and the risks of the digital divide. To address these challenges, a number of strategies were identified and subjected to critical evaluation to assess their practicality. Most of them were practical and align with the ethical and pedagogical theories. Within the prevalent concepts, “ChatGPT” emerged as the most frequent one, followed by “AI,” “student,” “research,” and “education,” highlighting a growing trend in educational discourse. Moreover, close collaboration was evident among the leading countries, all forming a single cluster, led by the United States. This comprehensive review provides implications, recommendations, and future prospects concerning the use of generative AI in education.
Filipa Campos, Angelica Sharma, Bijal Patel
et al.
Liver dysfunction can occur in patients presenting with thyrotoxicosis, due to several different aetiologies. A 42-year-old man had mild liver dysfunction on presentation with hyperthyroidism due to Graves’ disease (GD): ALT 65 (0–45 IU/L), fT4 41.2 (9–23 pmol/L), fT3 > 30.7 (2.4–6 pmol/L), and TSH < 0.01 (0.3–4.2 mIU/L). His liver dysfunction worsened following the initiation of the antithyroid drug (ATD) carbimazole (CBZ), with ALT reaching a zenith of 263 IU/L at 8 weeks following presentation. Consequently, CBZ was stopped, and he was managed with urgent radioiodine therapy. His liver function tests (LFTs) improved within 1 week of stopping carbimazole (ALT 74 IU/L). Thionamide-induced liver dysfunction is more typically associated with a ‘cholestatic’ pattern, although he had a ‘hepatitic’ pattern of liver dysfunction. The risk of liver dysfunction in GD increases with older age and higher titres of thyroid-stimulating hormone receptor antibody (TRAb). This review of the literature seeks to explore the possible causes of liver dysfunction in a patient presenting with hyperthyroidism, including thyrotoxicosis-induced liver dysfunction, ATD-related liver dysfunction, and the exacerbation of underlying unrelated liver disease.
This document represents the proceedings of the 2024 XCSP3 Competition. The results of this competition of constraint solvers were presented at CP'24 (30th International Conference on Principles and Practice of Constraint Programming).
This paper applies t-SNE, a visualisation technique familiar from Deep Neural Network research to argumentation graphs by applying it to the output of graph embeddings generated using several different methods. It shows that such a visualisation approach can work for argumentation and show interesting structural properties of argumentation graphs, opening up paths for further research in the area.
Many constraint satisfaction problems involve synthesizing subgraphs that satisfy certain reachability constraints. This paper presents programs in Picat for four problems selected from the recent LP/CP programming competitions. The programs demonstrate the modeling capabilities of the Picat language and the solving efficiency of the cutting-edge SAT solvers empowered with effective encodings.
As of 2020, the international workshop on Procedural Content Generation enters its second decade. The annual workshop, hosted by the international conference on the Foundations of Digital Games, has collected a corpus of 95 papers published in its first 10 years. This paper provides an overview of the workshop's activities and surveys the prevalent research topics emerging over the years.
The brain is often called a computer and likened to a Turing machine, in part because the mind can manipulate discrete symbols such as numbers. But the brain is a dynamical system, more like a Watt governor than a Turing machine. Can a dynamical system be said to operate using "representations"? This paper argues that it can, although not in the way a digital computer does. Instead, it uses phenomena best described using mathematic concepts such as chaotic attractors to stand in for aspects of the world.
In this paper, we provide an overview of the existing methods for integrating human advice into a Reinforcement Learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand. Finally, we review different approaches for integrating advice into the learning process.
Luc De Raedt, Sebastijan Dumančić, Robin Manhaeve
et al.
Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to identify a number of directions for further research.
The manuscript presented an analysis of the work in the field of eye-tracking over the past ten years in the low-cost filed. We researched in detail the methods, algorithms, and developed hardware. To realization, this task we considered the commercial eye-tracking systems with hardware and software and Free software. Additionally, the manuscript considered advances in the neural network fields for eye-tracking tasks and problems which hold back the development of the low-cost eye-tracking system. special attention in the manuscript is given to recommendations for further research in the field of eye-tracking devices in the low-cost field.
Bridge is a trick-taking card game requiring the ability to evaluate probabilities since it is a game of incomplete information where each player only sees its cards. In order to choose a strategy, a player needs to gather information about the hidden cards in the other players' hand. We present a methodology allowing us to model a part of card playing in Bridge using Probabilistic Logic Programming.
It is known due to the work of Van den Broeck et al [KR, 2014] that weighted first-order model counting (WFOMC) in the two-variable fragment of first-order logic can be solved in time polynomial in the number of domain elements. In this paper we extend this result to the two-variable fragment with counting quantifiers.
We present an executable formally verified SAT encoding of classical AI planning. We use the theorem prover Isabelle/HOL to perform the verification. We experimentally test the verified encoding and show that it can be used for reasonably sized standard planning benchmarks. We also use it as a reference to test a state-of-the-art SAT-based planner, showing that it sometimes falsely claims that problems have no solutions of certain lengths.
The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to precisely and consistently predict what specific actions a smarter-than-human intelligent system will take to achieve its objectives, even if we know terminal goals of the system. In conclusion, impact of Unpredictability on AI Safety is discussed.
This article applies the conceptual framework of constructor theory of information to cognition theory. The main result of this work is that cognition theory, in specific situations concerning for example the conjunction fallacy heuristic, requires the use of superinformation media, just as quantum theory. This result entails that quantum and cognition theories can be considered as elements of a general class of superinformation-based subsidiary theories.
Claudia Schon, Sophie Siebert, Frieder Stolzenburg
The CoRg system is a system to solve commonsense reasoning problems. The core of the CoRg system is the automated theorem prover Hyper that is fed with large amounts of background knowledge. This background knowledge plays a crucial role in solving commonsense reasoning problems. In this paper we present different ways to use knowledge graphs as background knowledge and discuss challenges that arise.
PIE is a Prolog-embedded environment for automated reasoning on the basis of first-order logic. It includes a versatile formula macro system and supports the creation of documents that intersperse macro definitions, reasoner invocations and LaTeX-formatted natural language text. Invocation of various reasoners is supported: External provers as well as sub-systems of PIE, which include preprocessors, a Prolog-based first-order prover, methods for Craig interpolation and methods for second-order quantifier elimination.
Some preliminary results are reported on the equivalence of any n-queens problem with the roots of a Boolean valued quadratic form via a generic dimensional reduction scheme. It is then proven that the solutions set is encoded in the entries of a special matrix. Further examination reveals a direct association with pointwise Boolean fractal operators applied on certain integer sequences associated with this matrix suggesting the presence of an underlying special geometry of the solutions set.
This note reviews Section 2 of Dung's seminal 1995 paper on abstract argumentation theory. In particular, we clarify and make explicit all of the proofs mentioned therein, and provide more examples to illustrate the definitions, with the aim to help readers approaching abstract argumentation theory for the first time. However, we provide minimal commentary and will refer the reader to Dung's paper for the intuitions behind various concepts. The appropriate mathematical prerequisites are provided in the appendices.