Search for dissertations about: "Out-of-Distribution"

Showing result 1 - 5 of 11 swedish dissertations containing the word Out-of-Distribution.

2. 1. On Improving Validity of Deep Neural Networks in Safety Critical Applications

   Author : Jens Henriksson; Chalmers tekniska högskola; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; out-of-distribution; outlier detection; deep neural networks; Safety critical applications;

   Abstract : Context: Deep learning has proven to be a valuable component in object detection and classification, as the technique has shown an increased performance throughput compared to traditional software algorithms. Deep learning refers to the process, in which an optimisation process learns an algorithm through a set of labeled data, where the researcher defines an architecture rather than the algorithm itself. READ MORE

4. 2. Outlier Detection as a Safety Measure for Safety Critical Deep Learning

   Author : Jens Henriksson; Chalmers tekniska högskola; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; outlier detection.; out-of-distribution; automotive perception;

   Abstract : Context: Deep learning (DL) has proven to be a valuable component in object detection and semantic segmentation tasks, as the techniques have shown significant performance gains compared to hand-made image processing algorithms. DL refers to an optimization process where a model learns properties and parameters itself through in iterative process running on labeled data. READ MORE

5. 3. Neural networks in context: challenges and opportunities : a critical inquiry into prerequisites for user trust in decisions promoted by neural networks

   Author : Lars Holmberg; Paul Davidsson; Per Linde; Carl Magnus Olsson; Maria Riveiro; Malmö universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Explainable AI; Machine Learning; Neural Network; Concept; Generalisation; Out-of-Distribution; Förklaringsbar AI; Maskininlärning; Neurala Nätverk; Koncept; Generalisering; Utanför-distributionen;

   Abstract : Artificial intelligence and machine learning (ML) in particular increasingly impact human life by creating value from collected data. This assetisation affects all aspectsof human life, from choosing a significant other to recommending a product for us to consume. READ MORE

6. 4. Towards safe and efficient application of deep neural networks in resource-constrained real-time embedded systems

   Author : Siyu Luan; Zonghua Gu; Leonid B. Freidovich; Lei Feng; Umeå universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Machine Learning Deep Learning; Real-Time Embedded systems; Out-of-Distribution Detection; Distribution Shifts; Deep Reinforcement Learning; Model Compression; Policy Distillation.;

   Abstract : We consider real-time safety-critical systems that feature closed-loop interactions between the embedded computing system and the physical environment with a sense-compute-actuate feedback loop. Deep Learning (DL) with Deep Neural Networks (DNNs) has achieved success in many application domains, but there are still significant challenges in its application in real-time safety-critical systems that require high levels of safety certification under significant hardware resource constraints. READ MORE

7. 5. Learning-based prediction, representation, and multimodal registration for bioimage processing

   Author : Nicolas Pielawski; Carolina Wählby; Thomas Walter; Uppsala universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Deep learning; Multimodal image registration; bayesian optimization; Bioimage processing; Computerized Image Processing; Datoriserad bildbehandling;

   Abstract : Microscopy and imaging are essential to understanding and exploring biology. Modern staining and imaging techniques generate large amounts of data resulting in the need for automated analysis approaches. READ MORE