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 10 of 10 for “"Negative Transfer"”.
-
Defining and Analyzing Negative Policy Transfer: National Orphan Drug Regulatory Policy in Canada and Australia
The existing policy transfer literature has largely ignored the study of negative transfer, resulting in various conceptualizations and a lack of tools for examining these cases. This study develops a novel analytical framework for explaining negative transfer, focusing on the three major pathways …
-
Multi-source domain adaptation with mixture of experts
… multiple baselines and can robustly handle negative transfer.
-
Application-specific transfer learning over edge networks
Transfer learning uses a profound labeled set of data from the source domain to deal with a similar problem for the target domain. Transfer learning provides accurate decision- making when insufficient data samples are available and when building a new prediction model takes more time and effort. …
-
Authentic science in education: Studies in course-based research at the United States Military Academy
… study in this dissertation adds an additional transfer focus to the instructional materials that the CURE was meant to support. The treatment group in this study received instruction that was framed expansively. The expansively framed instruction showed students ways that the material was …
-
A Machine Learning Approach for Forecasting with Limited Data and for Distant Time Horizons
… necessary to train deep neural networks. We use transfer learning with a weight sharing algorithm and observe that it improves all seven target model accuracies even after they have accumulated two weeks of their own data. However, the input data to transfer knowledge from must be chosen wisely …
-
The production and perception of Libyan Arabic stress patterns by English speaking learners: A comparison with native speakers
… pattern does not exist in the L1, then the L1 negative transfer effect may appear in the L2. The misperception of stress is not only restricted to L2 learners but native speakers also fail in certain patterns to perceive the stress location. The learners use grammatical class and syllable …
-
Computationally efficient Gaussian Process changepoint detection and regression
… and is theoretically guaranteed to prevent negative transfer. UCRL-GP-CPD is demonstrated empirically on a variety of simulated and real domains.
-
Learning With An Insufficient Supply Of Data Via Knowledge Transfer And Sharing
… is not readily available, knowledge has to be transferred from other sources and new methods (both supervised and un-supervised) have to be developed to selectively share and transfer knowledge. In this dissertation, we present both supervised and un-supervised techniques to tackle a problem …
-
Enhancing Compound Flood Modeling through Efficient Data-Driven, Physics-based, and Transfer Learning Frameworks
… configuration requirements limit model transferability to adjacent and/or distant coastal systems. Conversely, advanced data-driven approaches (e.g., deep learning) offer substantial advantages in terms of computational efficiency with faster model predictions across model domains. Yet, …
-
Representation decomposition for knowledge extraction and sharing using restricted Boltzmann machines
… and complex deep networks; (iii) an adaptive transfer learning method for knowledge reuse. These capabilities are the fundamentals of a Learning, Extraction and Sharing (LES) system, which we have developed. In this system learning can automate the process of encoding knowledge from data into …