Sökning: "label noise"

Visar resultat 1 - 5 av 13 avhandlingar innehållade orden label noise.

1. 1. On Medical Image Segmentation With Noisy Labels

   Författare :Marcus Nordström; Henrik Hult; Atsuto Maki; Fredrik Kahl; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Medical image segmentation; image segmentation; machine learning; supervised learning; label noise; Sörensen-Dice coefficient; soft-Dice; Medicinsk bildsegmentering; bildsegmentering; maskininlärning; övervakat lärande; annoteringsbrus; Sörensen-Dice koefficienten; soft-Dice; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics; Mathematical Statistics; Matematisk statistik;

   Sammanfattning : It is well known that data sets used for training and testing automatic medical image segmentation methods often contain a lot of label noise. Such noise affects the performance of the methods and has been subject to a lot of research. LÄS MER

3. 2. Silicon Nanowire Field-Effect Devices as Low-Noise Sensors

   Författare :Xi Chen; Zhen Zhang; Shi-Li Zhang; Si Chen; Fengnian Xia; Uppsala universitet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Silicon nanowire; field-effect transistor; Schottky junction gate; low frequency noise; ion sensor; Teknisk fysik med inriktning mot elektronik; Engineering Science with specialization in Electronics;

   Sammanfattning : In the past decades, silicon nanowire field-effect transistors (SiNWFETs) have been explored for label-free, highly sensitive, and real-time detections of chemical and biological species. The SiNWFETs are anticipated for sensing analyte at ultralow concentrations, even at single-molecule level, owing to their significantly improved charge sensitivity over large-area FETs. LÄS MER

4. 3. On Uncertainty Quantification in Neural Networks: Ensemble Distillation and Weak Supervision

   Författare :Amanda Olmin; Fredrik Lindsten; Lennart Svensson; Hossein Azizpour; Linköpings universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

   Sammanfattning : Machine learning models are employed in several aspects of society, ranging from autonomous cars to justice systems. They affect your everyday life, for instance through recommendations on your streaming service and by informing decisions in healthcare, and are expected to have even more influence in society in the future. LÄS MER

5. 4. Unsupervised Segmentation of Head Tissues from Multi-Modal Magnetic Resonance Images: With Application to EEG Source Localization and Stroke Detection

   Författare :Mahmood Qaiser; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; stroke; EEG source localization; Image segmentation; reconstruction; magnetic resonance; brain;

   Sammanfattning : The automated segmentation or labeling of individual tissues in magnetic resonance (MR) images of the human head is an essential first step in several biomedical applications. The resulting segmentation yields a patient-specific labeling of individual tissues that can be used to quantitatively characterize these tissues (e.g. LÄS MER

7. 5. Pushing the Boundaries of Biomolecule Characterization through Deep Learning

   Författare :Henrik Klein Moberg; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Computer Vision; Optical Microscopy; Artificial Intelligence; Biological Imaging; Molecule Characterisation; Deep Learning; Nanofluidic Scattering Microscopy;

   Sammanfattning : The importance of studying biological molecules in living organisms can hardly be overstated as they regulate crucial processes in living matter of all kinds. Their ubiquitous nature makes them relevant for disease diagnosis, drug development, and for our fundamental understanding of the complex systems of biology. LÄS MER