Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 19 of 19 for “"AI reasoning"”.
-
Causal Graphical Models in AI Reasoning & Expert Decision-Making
… of the world to reason under uncertainty. These internal world models can encode beliefs about cause-effect relationships, supporting causal reasoning in novel and uncertain environments. Probability theory and causal inference provide principled frameworks that further aid humanity …
-
Fusion of Knowledge: Enhancing AI Reasoning through Language Models and Knowledge Graphs
… as important areas in Artificial Intelligence (AI). LLMs leverage vast amounts of unstructured text to understand and generate natural language. KGs are relational graphs that encode domain expertise and knowledge into explicit semantics. A desideratum of AI is the ability to reason and draw …
-
An Empirical Study of Differences Between Human and AI Reasoning in Security-Related Tasks
… security-related tasks that involve perception, reasoning, and decision making. Although these models achieve strong performance on many benchmarks, their reasoning processes, driven primarily by statistical pattern matching, local feature extraction, and contextual coherence, differ …
-
PhishGuard: Transparent Email Security Using A Dual Model Architecture
Phishing remains one of the most pervasive threats to digital communication, exacerbated by the rise of generative AI and advanced social engineering techniques. This work presents Phish-Guard, a privacy-aware architecture that combines natural language processing (NLP) modules with small language …
-
Auditing the Reasoning Processes of Medical-Image AI
While medical artificial intelligence (AI) systems are achieving regulatory approval and clinical deployment across the world, the reasoning processes of these systems remain opaque to all stakeholders, including physicians, patients, regulators, and even the developers of these systems. Since the …
-
Exploring the Effects of Explainable Artificial Intelligence (XAI) Across AI Tools with Different Levels of Decision Complexity
… research examines how visual and textual Explainable Artificial Intelligence (XAI) explanations influence users’ trust and mental model clarity in AI recommendation systems. Using a 2 × 3 mixed factorial experiment, the study compared visual and textual explanations across three decision tasks …
-
Low-Resource Ecoacoustic Audio Classification
… enables scalable analysis but is often constrained by labeled data scarcity, particularly in remote regions like the Arctic. This thesis confronts low-resource ecoacoustic audio classification by developing and evaluating complementary machine learning methodologies. We introduce EDANSA, the …
-
A FRAMEWORK FOR TEXT SIMPLIFICATION IN LANGUAGE TO LOGIC TRANSLATION
… into logical equivalents enables automated reasoning, but the complexity of natural language hinders translation into formal representations such as the Standard Upper Ontology Knowledge Interchange Format. The proposed Hybrid Neuro-Ontological Language Understanding project addresses this …
-
Deep Learning and evidential reasoning for software vulnerability analysis
… analyse code from a weakness perspective, chaining these weaknesses across multiple components and employing techniques that exploit poor safety measures more than outright vulnerabilities. Therefore, a method is required that can detect these weaknesses, known as risk signals, chain or …
-
Writing for Each Other: Dynamic Quest Generation Using in Session Player Behaviors in Mmorpg
… rely on interesting and varied experiences to maintain player attention. These experiences are often provided through quests, which give players tasks that are used to advance stories or events unfolding in the game. Traditional quests in video games require very specific conditions to be met, …
-
Towards an Intelligent Built Environment: Digital Building Logbooks and AI Systems for Managing and Reasoning over BIM Data
… In parallel, Artificial Intelligence (AI) offers new opportunities to make this information more usable and actionable throughout a building’s lifecycle. This thesis advances the vision of an Intelligent Built Environment by presenting two complementary research directions: Digital …
-
Deep Combinatorial Reasoning: From Games To Scientific Discovery
… intricacies of combinatorial realms, such as in AI planning and scientific discovery, continue to pose formidable challenges to RL methodologies. The main difficulty in these domains is that the occurrence of a positive reward signal becomes increasingly rare as the minimal solution length or the …
-
Belief Change in Reasoning Agents
… research fields in Artificial Intelligence (AI) for over two decades. In the AI literature, two different kinds of belief change operations have been intensively investigated: belief update, which deal with situations where the new information describes changes of the world; and belief …
-
Toward spatial intelligence: structured visual generation and verifiable 3D reasoning
… This dissertation investigates how AI can achieve genuine spatial intelligence through three complementary lines of work spanning generative modeling, neural 3D geometry, and verifiable evaluation. First, we present two published works on the internal structure of rectified flow …
-
Solving the Bongard Problems with Language and Code
… the puzzling ability to deploy their visualreasoning abilities in radically new situations – a skill rigorously tested by the classic set of visual reasoning challenges known as the Bongard problems. We present a neurosymbolic approach to solving these problems: given a hypothesized solution …
-
C-XAI: Design Method for Explainable AI Interfaces to Enhance Trust Calibration.
Human-AI collaborative decision-making tools are on an accelerated rise in several critical application domains, such as healthcare and military sectors. It is often difficult for users of such systems to understand the AI reasoning and output, particularly when the underlying algorithm and logic …
-
Ανάπτυξη συστήματος λήψης αποφάσεων με έμφαση στην υποβοήθηση πρόγνωσης και διάγνωσης στην πυρηνική ιατρική
… complexity of medical image analysis. While AI has demonstrated remarkable potential in medical diagnosis, widespread clinical adoption faces a critical barrier: the "black box" problem. Clinicians require transparent, interpretable AI systems that provide not just predictions but also clear …
-
Symbolic Neural Reasoning for Visual Question Answering
… world. However, the ability of the most advanced AI agents to tackle complex logical reasoning remains ongoing challenge. For example, as the complexity of logical queries and inference increases, the performance of VQA systems and LVMs tends to decline. But on which types of logical questions …
-
Process-Grounded Knowledge-Infused Learning and Decision Making
… process-grounded knowledge-infused learning and reasoning, a novel framework for integrating domain-expertise-based process knowledge into the learning and reasoning mechanisms of artificial intelligence systems. This approach is designed to produce controlled, transparent, and reliable …