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 14 of 14 for “"Interpretable AI"”.
-
Towards More Interpretable AI With Sparse Autoencoders
… remarkable capabilities across diverse domains, the specific representations and algorithms they learn remain largely unknown. The quest to understand these mechanisms holds dual significance: scientifically, it represents a fundamental inquiry into the principles underlying intelligence, …
-
Building Modular, Human-Interpretable AI Systems with Behavior Trees
… candidate for constructing solutions for many AI applications, advantages includes readily changeable and human-interpretable. Two main topics covered in this thesis are: 1) IKBT: solving inverse kinematics with behavior trees. IKBT demonstrates how manually designed behavior trees with …
-
Towards Interpretable AI for Longitudinal Disease Monitoring and Clinical Reporting from Chest X-Rays
… learning, disease progression monitoring remains relatively underexplored. Challenges arise from the specificity of biomarkers that detect change, which vary in their mechanisms, manifestations, and progression rates across diseases, alongside individual variability in response to illness and …
-
AI-informed model analogs for subseasonal-to-seasonal prediction
… preparedness, and agriculture, and yet it remains a particularly challenging timescale to predict. We explore the use of an interpretable AI-informed model analog forecasting approach, previously employed on longer timescales, to improve S2S predictions. Using an artificial neural network, we …
-
Explainable AI Methods For Enhancing AI-Based Network Intrusion Detection Systems
… developing advanced artificial intelligence (AI) techniques for intrusion detection systems (IDS). However, the reliance on AI for IDS presents challenges, including the performance variability of different AI models and the lack of explainability of their decisions, hindering the …
-
Multimodal Representation Learning for Agentic AI Systems
Modern artificial intelligence (AI) is poised to transform the scientific process, from ideation and experimentation to peer review. Many researchers posit that emerging generalist AI “agents” will soon no longer be mere tools, but equal partners in scientific exploration. In this work, we …
-
Towards Interpretable Vision Systems
Artificial intelligent (AI) systems today are booming and they are used to solve new tasks or improve the performance on existing ones. However, most AI systems work in a black-box fashion, which prevents the users from accessing the inner modules. This leads to two major problems: (i) users have …
-
An Interpretable Multimodal Framework for Regional Organ Transplantation Outcomes
… supply, with over 89,792 patients on the waitlist as of September 2024, yet only 27,332 transplants performed in 2023 [1], and 28% of recovered kidneys going non-utilized [2]. In this thesis, we highlight the use of large language model (LLM) embeddings combined with structured tabular data …
-
An Explainable Artificial Intelligence Approach Based on Deep Type-2 Fuzzy Logic System
Artificial intelligence (AI) systems have benefitted from the easy availability of computing power and the rapid increase in the quantity and quality of data which has led to the widespread adoption of AI techniques across a wide variety of fields. However, the use of complex (or Black box) AI …
-
Practical Diagnostic Tools for Deep Neural Networks
The most common way to evaluate AI systems is by analyzing their performance on a test set. However, test sets can fail to identify some problems (such as out-of-distribution failures) and can actively reinforce others (such as dataset biases). Identifying problems like these requires techniques …
-
Towards Bridging and Governing Decentralized Communities
… subject to one-size-fits-all policies that fail to address local contexts. Consequently, toxic behavior is policed at the platform level rather than by the communities themselves, leading to oversimplified governance solutions that favor some communities while silencing others. Fortunately, …
-
Deep concept reasoning: beyond the accuracy-interpretability trade-off
… models can achieve superhuman performances, explaining deep learning decisions and mistakes is often impossible even for "explainable AI" specialists, causing lawmakers to question the ethical and legal ramifications of deploying deep learning systems. For this reason, the key open problem in the …
-
Transcriptional regulatory genomics: from mechanistic modeling to causal inference
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms