Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo
Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo
Theses and Dissertations
Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …
Uncertainty Estimation Of Deep Neural Networks, Chao Chen
Uncertainty Estimation Of Deep Neural Networks, Chao Chen
Theses and Dissertations
Normal neural networks trained with gradient descent and back-propagation have received great success in various applications. On one hand, point estimation of the network weights is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. On the other hand, exact Bayesian neural network methods are intractable and non-applicable for real-world applications. To date, approximate methods have been actively under development for Bayesian neural networks, including but not limited to: stochastic variational methods, Monte Carlo dropouts, and expectation propagation. Though these methods are applicable for current large networks, there are limits to these approaches with either underestimation …
Improving The Analyst And Decision-Maker’S Perspective Through Uncertainty Visualization, Evan T. Watkins
Improving The Analyst And Decision-Maker’S Perspective Through Uncertainty Visualization, Evan T. Watkins
Theses and Dissertations
This thesis constructs the Taxonomy of Uncertainty and an approach for enhancing the information in decision support systems. The hierarchical categorization of numerous causes for uncertainty defines the taxonomy, which fostered the development of a technique for visualizing uncertainty. This technique is fundamental to expressing the multi-dimensional uncertainty that can be associated with any object. By including and intuitively expressing uncertainty, the approach facilitates and enhances intuition and decision-making without undue information overload. The resulting approach for enhancing the information involves recording uncertainty, identifying the relevant items, computing and visualizing uncertainty, and providing interaction with the selection of uncertainty. A …
On Unifying Time And Uncertainty: The Probabilistic Temporal Network, Joel D. Young
On Unifying Time And Uncertainty: The Probabilistic Temporal Network, Joel D. Young
Theses and Dissertations
Complex real-world systems consist of collections of interacting processes/events. These processes change over time in response to both internal and external stimuli as well as to the passage of time. Many domains such as real-time systems diagnosis, (mechanized) story understanding, planning and scheduling, and financial forecasting require the capability to model complex systems under a unified framework to deal with both time and uncertainty. Existing uncertainty representations and existing temporal models already provide rich languages for capturing uncertainty and temporal information, respectively. Unfortunately, these partial solutions have made it extremely difficult to unify time and uncertainty in a way that …