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 7 of 7 for “"Feature-sharing"”.
-
Reinforced co-learning for semi-supervised ranking
… reflected in the network structure. We add the feature sharing layer, which enables the classifier to distill its intermediate representations to the learning of reinforcement ranker module. Extensive experiments and ablation studies show that both our co-learning strategy and feature sharing …
-
The attentional cost of feature-based inhibition: When ignoring distraction impairs selection
… when the new and important information shares features with the old inhibited information. I extend previous preview-based research (Braithwaite & Humphreys, 2003) to more ecologically valid dynamic circumstances. This work reveals that the cost of feature sharing is greatly magnified when …
-
Visualizing and interpreting convolutional neural networks on genomic data
Deep learning's capability to learn derived features through a hierarchy of non-linear layers has proven superior to other machine learning methods. However, interpretation of the resulting genomic deep learning networks remains challenging. While many network visualization tools focus on directly …
-
The universality of concord
… and defend a universal theory of concord (i.e. feature sharing between a head noun and the modifying adjectives). When adjectives in a language show concord with the noun they modify, concord morphology usually involves the full set of features of that noun (e.g. gender, number and case). …
-
Resource management in sensing services with audio applications
… setting is achieved through the feature-sharing principle. Once applied, the method results in a system that can achieve 9x resource saving and 1.43x improvement in detection performance in an example application. Based on the encouraging results above, a prototype audio sensing …
-
Evaluating the interaction between material substitution and part sharing in product design : a case study of automotive lightweighting
… of the economies of scale. In this way, part sharing reduces the cost burden of maintaining multiple product variants. However, part sharing also reduces product differentiation by resulting in some feature sharing, as the requirements of component parts differ across different product …
-
Reliable and decentralised deep learning for physiological data
… To address this, a novel method based on feature sharing and augmentation is proposed to balance privacy protection and model performance. All proposed methods have been validated using real-world physiological datasets and commonly used machine learning benchmark data. Specific attention …