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 39 for “"model-agnostic"”.
-
Unsupervised Learning : Model-guided and Model-agnostic Approaches
… of such large amounts of labeled data for these models makes one skeptical about the generalization of such intelligence to myriad tasks. While training a neural network to classify images of a cat, one might wonder : Do humans really need hundreds of images to differentiate a cat from an …
-
Model-agnostic Methodology for High-Altitude Balloon Mission Planning
… resilient communications. There is a need for modeling HABs in multi-domain missions, and a key challenge for incorporating them is their flight trajectory dependence on atmospheric conditions. The difficulty in working with atmospheric conditions is that forecasts can only be relatively …
-
ULIME: Uniformly weighted Local Interpretable Model-agnostic Explanations for Image Classifiers
… rapid development of complex machine learning models, there is uncertainty on how these models truly work. Their black-box nature restricts experts from evaluating models solely on standard numerical metrics, which may result in a model performing seemingly well on a dataset but for the wrong …
-
Multi-scale local explanation approach for image analysis using model-agnostic explainable artificial intelligence (XAI)
… for the broad adoption of deep learning based models such as Convolutional Neural Networks (CNN) is the lack of understanding of their decisions. Local Interpretable Model-agnostic Explanations (LIME) is an explanation method which produces a coarse heatmap as a visual explanation highlighting …
-
Supporting Human Performance with Post-hoc Explanations in Automated Decision Assistance
… two controlled experiments on the effects of model-agnostic explanations on human performance in an industrial application where effective and efficient detection of system failure is critical to ensure operational continuity. The experiments tested different combinations of example-based …
-
Conformal Methods for Efficient and Reliable Deep Learning
… over the last decade. As large foundation models continue to evolve and be deployed into real-life applications, an important question to ask is how we can make these expensive, inscrutable models more efficient and reliable. In this thesis, we present a number of fundamental techniques for …
-
Few-Shot Semi-Supervised Robust Text Classification with MAML
… of a supervised meta-learning algorithm (Model-Agnostic Meta-Learning) applied to few-shot natural language text classification tasks. We also detail a way to incorporate semi-supervised learning into MAML by designing a procedure to create self-supervised tasks from unlabeled text …
-
Source Separation using Sparse Bayesian Learning
… our agents are noncooperative, we must develop a model-agnostic approach at tackling this problem. For this work, we will consider cohabitation between radar signals and communication signals, with the former being the desired signal and the latter being the noncooperative agent. In order to …
-
Learning to fly : computational controller design for hybrid UAVs with reinforcement learning
… this design process by training a mode-free, model-agnostic neural network controller for hybrid UAVs. We present a neural network controller design with a novel error convolution input trained by reinforcement learning. Our controller exhibits two key features: First, it does not distinguish …
-
Explainable AI: A Unified Approach Based on Cooperative Game Theory
… the interpretability of machine learning (ML) models, yet existing feature-based explanation methods remain fragmented across local and global approaches. This thesis presents a unified framework based on cooperative game theory to systematically characterize and distinguish feature-based …
-
Interpretable and Automated Bias Detection for AI in Healthcare
… sources of bias in healthcare datasets and AI models. Our framework is data and model agnostic and does not rely on human-developed heuristics or assumptions to uncover bias. We demonstrate its effectiveness by uncovering serious and nontrivial sources of bias in three widely used clinical …
-
Inductive logic programming with gradient descent for supervised binary classification
… interpretability has become a major concern for models making important decisions. In contrast to Local Interpretable Model-Agnostic Explanations (LIME), this thesis seeks to develop an interpretable model using logical rules, rather than explaining existing blackbox models. We extend recent …
-
Data Centric Defenses for Privacy Attacks
… sensitive information about the data used in model training. These attacks called privacy attacks, exploit the model training process. Contemporary defense techniques make alterations to the training algorithm. Such defenses are computationally expensive, cause a noticeable privacy-utility …
-
Interpreting black-box models through sufficient input subsets
… a reputation of producing opaque, "black-box" models. While deep neural networks are often able to achieve superior predictive accuracy over traditional models, the functions and representations they learn are usually highly nonlinear and difficult to interpret. This lack of interpretability …
-
Exploring Smallholder Field Delineation
… agricultural monitoring. However, most existing models are developed and evaluated in large-scale, industrial agricultural regions, where field boundaries are relatively regular and high-quality annotated data is more readily available. In contrast, smallholder regions—where fields are smaller, …
-
Data-Efficient Machine Learning with Applications to Cardiology
Deep learning models have demonstrated impressive capabilities in many settings including computer vision, natural language generation, and speech processing. However, an important shortcoming of these models is that they often need to be trained on large datasets in order to be most effective. In …
-
Investigating the Use of Inductive Transfer Learning and RNN to Quantify Extreme Event Statistics of Ship Motions
… through inductive transfer learning and a model agnostic meta-learning approach, one that leverages the training of previous networks to augment SimpleCode across a broader range of seas or produce more accurate results on a narrow set of sea conditions after very few training samples.
-
Zero-Shot Scene Graph Relationship Prediction using VLMs
… target dataset, even when using Vision-Language Models (VLMs). In this work, we propose a training-free framework for the VLMs to predict scene graph relationships. Our approach simply plugs VLMs into the pipeline without any fine-tuning, focusing on how to formulate relationship queries and …
-
Deep Hedging of basis risk
… the hedge parameters are determined in a model agnostic way. This is achieved using Long Short-Term Memory networks written in TensorFlow. This allows one to make the hedge parameters at each time point a function of current market data and previous hedging decisions. Deep Hedging is …
-
A Multitask Deep Learning Framework for Clinical Decision-Making in Assisted Reproductive Technology
… pipeline evaluates classical statistical models, ensemble methods (XGBoost), and novel architectures, including TabPFN, an attention-based probabilistic model that achieved comparable performance to top-performing baselines. To enhance clinical trust, we apply SHapley Additive exPlanations …
Page 1 of 2