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 20 of 62 for “"Complex Reasoning"”.
-
Incidental Decomposition for Complex Reasoning
… emulating human cognitive processes that involve complex reasoning with decomposed understanding. Compared with humans, who continually learn from daily experiences, decompose decision-making processes, and form new associations, machine learning systems often have difficulty doing the same …
-
Structured Information Extraction and Applications in Complex Reasoning
… of structured information and its application to complex reasoning tasks. For structured information extraction, we focus on temporal information extraction, particularly on temporal normalization. Through systematic comparative experiments, we propose a strategy that enhances the generalization …
-
Chart Question Answering with Visual and Logical Reasoning
… data. When exploring charts, people often ask complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their …
-
The psychological construction of confusion and its relationship to complex inferential reasoning performance in a learning environment
… engage in tasks and activities that require complex thinking or inferential reasoning. In turn, many educationalists have responded to this finding by attempting to intensify the cognitive rigor of learning tasks given to students. But this strategy alone may prove ineffective because …
-
Reasoning in the Wild
… opening up new possibilities for automated reasoning. Although existing benchmarks have demonstrated strong reasoning performance of LMs, it remains unclear how effectively such models reason in real-world scenarios, where queries differ significantly in complexity and style from the …
-
A decision support system for the reading of ancient documents
… this process in the five areas: remembering complex reasoning, searching huge datasets, international collaboration, publishing editions, and image enhancement.</p> <p>This research contains a large practical element involving the development of a DSS prototype. The prototype is used to …
-
Elicit: Expertise Learner and Intelligent Causal Inference Tool
… systems are tools for solving difficult and complex problems for which standard algorithmic methods of solution are inadequate. The published literature describes very few knowledge-based systems developed to aid in solving complex reasoning tasks encountered in engineering. Planning, …
-
Multimodal Representation Learning for Textual Reasoning over Knowledge Graphs
… from KGs is generally achieved through logical reasoning, but this process can be computationally expensive and has limited performance due to the large size and complexity of relationships within the KGs. Furthermore, to extend the usage of KGs to non-expert users, retrieval over them cannot …
-
Analysis of item difficulty and change in mathematical achievement from 6th to 8th grade's longitudinal data
… needed in higher levels of mathematics and complex reasoning ability based on the developmental perspectives on cognition (e.g., Piaget, Vygotsky). The purpose of the current study was to measure and interpret the mathematical achievement growth during the middle school years using some very …
-
Robust, interpretable, and usable entity representations
… Additionally, entity knowledge can involve complex reasoning, in addition to relational knowledge. This type of inference capability is not tested by existing knowledge probing benchmarks. Furthermore, LMs' entity knowledge is frozen at the time of pretraining while the real world changes as …
-
Using semantic structure of the data and knowledge in question answering systems
Understanding and reasoning over natural language is one of the most crucial and long-standing challenges in Artificial Intelligence (AI). Question answering (QA) is the task of automatically answering questions posed by humans in a natural language form. It is an important criterion to evaluate …
-
Statistical and Machine Learning Methods for Neuroimaging and Neurocognitive Data
… of statistical and machine learning methods for complex, multi-modal, and high-dimensional data such as images, networks, and functions. Chapter 2 introduces a fully automated pipeline for identifying severe brain swelling in brain images from low-field magnetic resonance imaging (MRI), involving …
-
Towards Reliable and Practical Language-Model Agents: Evaluation and Development
While Large Language Model (LLM) agents with complex reasoning and tool-use capabilities are promising, their fundamental unreliability like hallucination hinders practical, high-stakes deployment. This thesis confronts this gap by diagnosing key facets of this unreliability and proposing a more …
-
A case-based reasoning approach to improve risk identification in construction projects
… reasons for this are investigated as accuracy, complexity, time and cost involved and lack of knowledge sharing. Appropriate risk identification is fundamental for successful risk management. Well known risk identification methods require expert knowledge, hence risk identification depends on …
-
Learning About Chemical Reactions in Digital Learning Environments
… proved particularly powerful for capturing complex reasoning that often remains invisible in traditional tests. Analyses of task and learner characteristics highlight the central role of prior knowledge and the influence of chemical representations on learning about chemical reactions. …
-
INVESTIGATING REASONING MODELS: OVERTHINKING AND THINKING EPISODE THEORY
… models (LLMs) have made remarkable progress in complex reasoning tasks by generating explicit chains of thought. However, the quality, efficiency, and structure of these reasoning processes remain poorly understood. This thesis investigates reasoning models through three complementary studies. …
-
Scalable Data Paradigms for Steering General-Purpose Language Models
… chatting with users, using tools, or performing complex reasoning, poses another set of challenges that require diverse, high-quality, and increasingly costly training data. This dissertation explores scalable paradigms for structuring, creating, and optimizing data to facilitate the broader …
-
Hierarchical policy design for sample-efficient learning of robot table tennis through self-play
… This work studies sample-efficient learning of complex policies in the context of robot table tennis. It incorporates learning into a hierarchical control framework using a model-free strategy layer (which requires complex reasoning about opponents that is difficult to do in a model-based way), …
-
Do Programs Designed To Train Working Memory, Other Executive Functions, And Attention Benefit Children With Adhd? A Meta-analytic Review Of Cognitive, Academic, And Behavioral Outcomes
… social functioning, academic performance, and complex reasoning skills. The present review critically evaluates these claims through meta-analysis of 25 studies of facilitative intervention training (i.e., cognitive training) for children with ADHD. Random effects models corrected for …
-
A qualitative theory of gas dynamics
… the problem of how to perform qualitative reasoning with computer programs has received considerable attention. The research field of qualitative physics focuses on the special problems of identifying the basic concepts of nature and the issues related to mechanizing inference about these …
Page 1 of 4