Sökning: "end-to-end learning"

Visar resultat 16 - 20 av 35 avhandlingar innehållade orden end-to-end learning.

1. 16. Competitive Learning in Robust Communication

   Författare :Petter Knagenhjelm; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

   Sammanfattning : A modern communication system should be accurate, reliable, robust and make efficient use of the available channel. Vector quantization is beginning to prove its effectiveness for source coding in applications such as cellular mobile telephony. The design of vector quantizers is typically done by clustering methods. LÄS MER

3. 17. Enhancing Machine Failure Detection with Artificial Intelligence and sound Analysis

   Författare :Thanh Tran; Jan Lundgren; Sebastian Bader; Domenico Capriglione; Mittuniversitetet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Machine Failure Detection; Machine Learning; Deep Learning; Sound Signal Processing; Audio Augmentation;

   Sammanfattning : The detection of damage or abnormal behavior in machines is critical in industry, as it allows faulty components to be detected and repaired as early as possible, reducing downtime and minimizing operating and personnel costs. However, manual detection of machine fault sounds is economically inefficient and labor-intensive. LÄS MER

4. 18. Deep learning approaches for image cytometry: assessing cellular morphological responses to drug perturbations

   Författare :Philip John Harrison; Ola Spjuth; Carolina Wählby; Andreas Hellander; Peter Horvath; Uppsala universitet; []
   Nyckelord :Deep Learning; Microscopy; Image Analysis; Farmaceutisk vetenskap; Pharmaceutical Science;

   Sammanfattning : Image cytometry is the analysis of cell properties from microscopy image data and is used ubiquitously in basic cell biology, medical diagnosis and drug development. In recent years deep learning has shown impressive results for many image cytometry tasks, including image processing, segmentation, classification and detection. LÄS MER

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

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

   Sammanfattning : 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. LÄS MER

7. 20. Applications in Monocular Computer Vision using Geometry and Learning : Map Merging, 3D Reconstruction and Detection of Geometric Primitives

   Författare :David Gillsjö; Matematik LTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Scene Completion; Deep Learning; Bayesian Neural Network; Room Layout Estimation; Line Segment Detection; Polygon Detection; Graph Neural Network; Map Merging; Structure from Motion; Minimal Solvers; Wireframe Estimation;

   Sammanfattning : As the dream of autonomous vehicles moving around in our world comes closer, the problem of robust localization and mapping is essential to solve. In this inherently structured and geometric problem we also want the agents to learn from experience in a data driven fashion. LÄS MER