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 8 of 8 for “"black box learning"”.
-
Unboxing the "Black Box": Learning Interpretable Deep Learning Features of Brain Aging
Deep learning (DL) algorithms are state-of-the-art techniques for automatic inference tasks like classification and regression in medical imaging and many other fields. Despite growing interest, DL models have had restricted implementation in practical settings as they are often considered to be …
-
Generalization in Machine Learning Through Information-Theoretic Lens
… to investigate generalization theory in machine learning, a critical area of research today. Specifically, we develop novel information-theoretic generalization bounds for machine learning algorithms. First, we apply information-theoretic analysis for models trained using stochastic gradient …
-
Interpretable approaches for condition monitoring, control, and energy optimization in electro-hydrostatic actuation systems
… To circumvent these challenges, a model-free learning strategy is introduced, consisting of offline and online phases. The controller parameters are initially tuned during the offline phase using a method known as augmented random search. The proposed method enables the transfer of offline …
-
Prior-guided Neural Compression of Visual Data
In recent years, deep learning methods have been widely applied in the field of visual data compression, some of which have delivered the best rate-distortion performances in history. The target domain of neural data compression started from that of still images and then rapidly expanded into …
-
SCALABLE AND RISK-AWARE VERIFICATION OF LEARNING ENABLED AUTONOMOUS SYSTEMS
… increasingly difficult due to the use of black box, learning enabled components and the growing range of operating domains in which they are deployed. The complexity of the learning-enabled components greatly increases the computational complexity of the verification problem. Additionally, …
-
Dependable Decision Making for Autonomous Vehicles Considering Perception Uncertainties
… (ADS), leveraging recent advancements in various learning algorithms, has demonstrated significant potential to enhance traffic safety. However, in the dynamic service environments, one of the crucial challenges in ADS safety evaluation is managing performance uncertainties inherent in these …
-
Learning Task Models for Robotic Manipulation of Nonrigid Objects
… One particularly challenging domain in robot learning is handling nonrigid objects and materials such as fluids and easily deformable parts and tools. The complexities of modeling nonrigid systems make it infeasible in general for a robot to plan its actions to perform a task by simulating …
-
Learning regular languages over large alphabets
Learning regular languages is a branch of machine learning, a domain which has proved useful in many areas, including artificial intelligence, neural networks, data mining, verification, etc. In addition, interest in languages defined over large and infinite alphabets has increased in recent years. …