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 59 for “"Symbolic Reasoning"”.
-
Neural-guidance for symbolic reasoning
Symbolic reasoning begot Artificial Intelligence (AI). With the recent advances in Deep Learning, many traditional AI areas such as Computer Vision and Natural Language Processing have moved to probabilistic-based approaches. However, in applications where there is little to no room for …
-
Symbolic Reasoning as a Library
… or optimization opportunities, and automated reasoning has emerged as a critical but challenging solution. %Building effective automated reasoning tools is challenging. However, advances in constraint solvers have shifted the engineering burden to symbolic compilation systems that translate …
-
Compositional Neuro-Symbolic Reasoning over Natural Language
… in the tradition of McCarthy (1959) pursued symbolic theorem proving over carefully hand-crafted ontologies of facts and rules. Due to challenges in scalability and expressivity, such reasoning has fallen out of favor in light of data-driven large language models (LLMs), which capture vast …
-
Integrating Symbolic Reasoning into Large Language Models
… models (LLMs) face fundamental challenges in symbolic reasoning, struggling with tasks requiring precise rule-following, logical consistency, and manipulation of structured representations. This thesis introduces a comprehensive neurosymbolic framework that addresses these limitations by …
-
Symbolic Reasoning for Query Verification and Optimization
… with learned predicates. I propose to use symbolic reasoning to address the limitations of syntax-driven approaches in these two problems. I first present two techniques for proving query equivalence under set and bag semantics based on symbolic representation. Both approaches are …
-
A Human-Centric System for Symbolic Reasoning About Code
… on all inputs without having to run the code. Symbolic reasoning is reasoning abstractly about code using arbitrary symbolic input values, as opposed to specific concrete inputs. The overarching goal of this research is to help students learn symbolic reasoning, beginning with code containing …
-
From Symbolic Reasoning to Object Embeddings: Advanced Approaches of Knowledge Distillation in Compacted Neural Networks
… also examines the integration of logical reasoning which addresses the shortcomings of current data-driven machine learning approaches. Such data-driven learning approaches are regarded as ``black-box" which often lack adequate reasoning behind their predictions. By combining logical …
-
Non-Axiomatic Reasoning and Causal Explorative System (NARCES), a Hybrid Symbolic Reasoning with Sub-symbolic Learning for Autonomous Intelligent Agents
In Artificial Intelligence, reasoning can be distinguished into symbolic and sub-symbolic. Symbolic reasoning makes use of formal language for semantic knowledge representations, as well as utilizes logic for inference, and system control for processing input and derived knowledge. The paradigm …
-
Learning to Reason About Code with Assertions: An Exploration with Two Student Populations
… to students’ understanding of a program, and symbolic reasoning that entails learning to use assertions with abstract input and output values, as opposed to concrete values, enhances that understanding. Symbolic reasoning teaches students valuable abstraction and logic skills that will serve …
-
Neurosymbolic Learning and Reasoning with OWL-based Knowledge Graphs
A central theme of Neurosymbolic AI involves combining subsymbolic learning with symbolic reasoning. Our research explores this theme using OWL ontologies and knowledge graphs to provide symbolic reasoning services within neurosymbolic systems. Our central research questions are: (i) how can we …
-
Neuro-symbolic program generation and execution for hybrid reasoning
Neuro-symbolic learning aims to combine neural networks and symbolic reasoning for a hybrid AI. It can offer many desiderata of human-like intelligence, including explainability, efficiency, compositionality, and robustness that are sorely lacking in the monolithic deep neural networks today. A …
-
Physics-aware Neuro-Symbolic AI for Spatial Computing
… by the Computing Community Consortium is neuro-symbolic AI, which merges the pattern-recognition strengths of neural networks with the reasoning ability of symbolic methods (logic programming, graph search). This integration has the potential to enhance neural networks by reducing hallucinations …
-
Structured temporal reasoning for video understanding
This thesis presents a neuro-symbolic approach to video understanding that addresses three fundamental tasks: video search, video question answering, and video generation evaluation. Each task is tackled through a unified framework that combines neural perception with formal symbolic reasoning via …
-
Seeing past the expert blind spot : developing a training module for in-service teachers
… are more likely to believe in the necessity of symbolic reasoning and mastery of equations as a prerequisite for algorithmic or mathematical problem solving. This pattern has been shown across several subject areas including mathematics, science, and language arts. While there has been a good …
-
Integrating textual queries with aI-based object detection: a compositional prompt-guided approach
… persist. This thesis presents a novel neuro-symbolic object detection framework that aligns object proposals with textual prompts using a deep learning module while enabling logical reasoning through a symbolic module. By integrating deep learning with symbolic reasoning, object detection and …
-
A Neuro-Symbolic Approach to Vision, Language, and Multi-Modal Reasoning
… and planning, the very strengths of classical symbolic reasoning. In "Thinking, Fast and Slow," Kahneman splits human cognition into a fast, intuitive "System 1," like neural networks, and a slow, logical "System 2," resembling symbolic reasoners. Modern foundation models increasingly combine …
-
Generalized Planning Using Language Models and Its Applications
… real-world applications that require fexible reasoning, robust decision- making, and the ability to operate across diverse environments. Large language models have emerged as powerful learners supported by their ar- chitectures and large-scale training data, demonstrating strong capabilities …
-
From batch to stream : automatic generation of online algorithms from offline implementations
… independent subtasks and uses a combination of symbolic reasoning and search to solve each subproblem. We implement the proposed technique in a new tool called Opera and evaluate it on over 50 tasks spanning two domains: statistical computations and online auctions. Our results show that Opera …
-
Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning
… also in the nontraditional task of training a symbolic reasoning engine. We observe that these engines learn quickly and generalize in a natural way that reflects human intuition. For example, training such a system to model block-stacking might naturally generalize to stacking other types of …
Page 1 of 3