Sökning: "Jens Henriksson"
Hittade 3 avhandlingar innehållade orden Jens Henriksson.
1. On Improving Validity of Deep Neural Networks in Safety Critical Applications
Sammanfattning : 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. LÄS MER
2. Outlier Detection as a Safety Measure for Safety Critical Deep Learning
Sammanfattning : 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. LÄS MER
3. Functional and Renewable Galactoglucomannan-based Hydrogels
Sammanfattning : Polysaccharides represent an important resource for a variety of products, from food via fuel supply to functional materials of every kind. Here they are, due to their natural diversity found in many special applications, e.g. in the biomedical sector. LÄS MER