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 71 for “"Robust training"”.
-
Deep Learning with Abstention: Algorithms for Robust Training and Predictive Uncertainty
… \textit{First, we study the problem of how to robustly train deep models when the training data itself is unreliable.} This is a common occurrence in real-world deep learning where large quantities of data can be easily collected, but due to the enormous size of the datasets required for deep …
-
Robust machine learning against unseen distributional shifts
… data distribution. To tackle this challenge, robust training emerges as a highly effective strategy for enhancing the OOD generalization ability of DNNs, enabling them to excel in complex and unpredictable real-world environments. This dissertation revolves around my extensive research on …
-
Towards robust neural networks: evaluation and construction
… care and finance. In this thesis, we study robust neural networks in the hope to facilitate a wider and more reliable use of neural networks. Specifically, we focus on evaluating and training robust neural networks.</p> <p>We first consider robustness evaluation. A common approach for …
-
Domain-centric Methods for Robust Speech Enhancement Models in Cochlear Implants in Dynamic Acoustic Environments
… the development of computationally efficient and robust speech enhancement approaches specifically designed for the constraints of CI signal processing.</p><p>This dissertation investigates machine learning-based speech enhancement strategies that leverage phonetic structure and domain-robust …
-
Communication Relaying Networks Using Autonomous Drones: Solving Cooperative Markov Games Using Multi-Agent Reinforcement Learning
Training several autonomous actors to solve cooperative tasks allows for systems with decentralized control and without single points of failure. One example is the use of swarms of drones to build quick and adaptable communication networks, allowing for efficient communication in hard-to-reach …
-
TOWARDS GENERALIZABLE AND EFFICIENT 3D SCENE RECONSTRUCTION
… text-to-image (T2I) diffusion models possess a robust, training-free capacity for novel view synthesis through DreamDrone, a zero-shot framework for perpetual view generation. Building on this strong generative capability, we leverage the prior knowledge of T2I models to facilitate 3D …
-
On Enabling Layer-Parallelism for Graph Neural Networks using IMEX Integration
… GNN architectures, which are suitable for robust training when equipped with a relatively large number of layers. Neural networks with more layers are potentially more expressive. However, the training time increases linearly with the number of layers. Parallel-in-layer training is a method …
-
CREATING A MORE CAPABLE SPECIAL OPERATIONS FORCE: INTERNATIONAL LESSONS FOR THE PHILIPPINE COAST GUARD
… mission parameters, inadequate specialized training, equipment shortfalls, and limited adaptability to evolving threats. In contrast, successful foreign units demonstrate clear mandates, comprehensive training balancing tactical and maritime skills, advanced equipment, and cultures of …
-
Weakly-Supervised Scaling for Open-Vocabulary Action Detection
… datasets with many action classes for robust training, and (2) parameter-heavy adaptations to a pretrained vision-language contrastive model to convert it for detection, risking overfitting the additional non-pretrained parameters to base action classes. Firstly, we introduce an …
-
A Litigation Analysis of the Extraterritoriality of U.S. Federal Laws in International Education
… faculty and administrative staff through robust training and coordination with campus offices such as their general counsel and disability services.
-
THE GHOST IN THE MACHINE: CBP POSITION CLASSIFICATION AND HIRING CULTURE MAKE FULL MISSION READINESS IMPOSSIBLE
… in the classification process, implementing robust training for hiring managers, and revising agency policies to enhance accountability and alignment with contemporary workforce requirements. The study contributes to the discourse on federal employment reforms that align classification …
-
RADIATION-HARDENED MICROELECTRONICS WORKFORCE DEVELOPMENT GUIDELINE
… The objective of the research is to develop a training plan/guideline for current and future workforce in the field of radiation-hardened microelectronics in order to provide them with the knowledge and skills needed to perform radiation effects testing, development, and analysis. This research …
-
An Examination of the Potentials and Limitations of Incorporating Digital Technologies within Community Health Workers Systems in Western Kenya
… strengthening infrastructure, providing robust training and support, enhancing data security policies, and establishing sustainable financing sources. Overcoming these barriers will enable stakeholders to maximize the impact of digital health tools on MCH outcomes and healthcare delivery, …
-
Self-supervised learning of musical representations using VICReg; a comprehensive study of the VICReg loss function for self-supervised representation learning in the music domain
… classification on the MagnaTagATune dataset by training a linear logistic classifier and a two-layer MLP classifier atop the representations generated by a frozen, pre-trained VICReg model. In our transfer learning experiments, VICReg achieves a ROC-AUC score of 89.15 and a PR-AUC score of 35.85 …
-
An evaluation of the power of kindness in primary aged children: a whole-class intervention
… possible solutions including an investment in robust training. Children offered invaluable perspectives in helping to understand the outcomes of the study.
-
Statistical Modeling of Knee Morphology and Material Properties Considering Diverse Populations
… further validation with a more balanced and robust training set is needed to confirm these findings. Finally, an innovative application to facilitate the utilization of these findings in the development of orthopedic devices was created. This work represents a significant step towards greater …
-
Bridging Technology and Therapy: Assessing the Quality and Analyzing the Impact of Human Editing on AI-Generated SOAP Notes in Pediatric Rehabilitation
… the necessity of human-AI collaboration and robust training to mitigate limitations such as contextual inaccuracies and misclassifications. These findings provide a foundation for future research and practical recommendations for integrating AI into healthcare documentation workflows.
-
On the use of email in further education
… for the development of appropriate and robust training to replace current training which is poorly engaged with.
-
Social Work and Psychedelics: Practice and Perspectives in Canada: An Exploratory Multiple Case Study
… for promoting ethical practice suggest robust training programs, regular clinical supervision, and the importance of community building among practitioners. The results of this study highlight considerations for how psychedelic treatment methods can be integrated into the field of social …
Page 1 of 4