Essays about: "Osäkerhetsskattning"
Found 4 essays containing the word Osäkerhetsskattning.
-
1. Uncertainty Estimation in Radiation Dose Prediction U-Net
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : The ability to quantify uncertainties associated with neural network predictions is crucial when they are relied upon in decision-making processes, especially in safety-critical applications like radiation therapy. In this paper, a single-model estimator of both epistemic and aleatoric uncertainties in a regression 3D U-net used for radiation dose prediction is presented. READ MORE
-
2. Uncertainty Estimation for Deep Learning-based LPI Radar Classification : A Comparative Study of Bayesian Neural Networks and Deep Ensembles
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep Neural Networks (DNNs) have shown promising results in classifying known Low-probability-of-intercept (LPI) radar signals in noisy environments. However, regular DNNs produce low-quality confidence and uncertainty estimates, making them unreliable, which inhibit deployment in real-world settings. READ MORE
-
3. Real-time Uncertainty Estimation for Semantic Segmentation : Improving Uncertainty Estimates with Temperature Scaling and Predicted Dirichlet Distributions
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This degree project examined different aspects of real-time uncertainty estimation for semantic segmentation deep learning networks in an autonomous driving setting. Two main tracks were taken. READ MORE
-
4. Neural Networks and Uncertainty Estimation for Financial Asset Predictions
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : With the capability of modeling complex non-linear mappings, neural networks have obtained state-of-the-art performance on various tasks. However, traditional neural networks are prone to overfitting as they tend to be overconfident on unseen, noisy and incorrectly labeled data. Neither do they produce meaningful representations of uncertainty. READ MORE