Sökning: "deep structure"

Visar resultat 21 - 25 av 267 avhandlingar innehållade orden deep structure.

1. 21. 3D Human Pose and Shape Estimation Based on Parametric Model and Deep Learning

   Författare :Zhongguo Li; Matematik LTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; 3D Human body; Implicit function; Deep Learning; SMPL model; Parametric model; Pose and shape estimation;

   Sammanfattning : 3D human body reconstruction from monocular images has wide applications in our life, such as movie, animation, Virtual/Augmented Reality, medical research and so on. Due to the high freedom of human body in real scene and the ambiguity of inferring 3D objects from 2D images, it is a challenging task to accurately recover 3D human body models from images. LÄS MER

3. 22. Measurement of azimuthal asymmetries in the hadronic final-state of deep inelastic scattering at HERA

   Författare :Magnus Lindström; Partikel- och kärnfysik; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; jets; DIS; azimuthal asymmetries; structure function; unfold; quantum field theory; Elementary particle physics; Elementarpartikelfysik; kvantfältteori; Physics; Fysik; Fysicumarkivet A:2000:Lindström;

   Sammanfattning : Azimuthal asymmetries of the hadronic final state in deep inelastic scattering at HERA provide the opportunity to study the helicity of the interacting particles. We present a theoretical overview of the origin of these effects up to leading order in the strong coupling constant, $alpha_s$. LÄS MER

4. 23. Protein Model Quality Assessment : A Machine Learning Approach

   Författare :Karolis Uziela; Arne Elofsson; Liam McGuffin; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Protein Model Quality Assessment; structural bioinformatics; machine learning; deep learning; support vector machine; proq; Artificial Neural Network; protein structure prediction; Biochemistry towards Bioinformatics; biokemi med inriktning mot bioinformatik;

   Sammanfattning : Many protein structure prediction programs exist and they can efficiently generate a number of protein models of a varying quality. One of the problems is that it is difficult to know which model is the best one for a given target sequence. Selecting the best model is one of the major tasks of Model Quality Assessment Programs (MQAPs). LÄS MER

5. 24. Integrating domain knowledge into deep learning : Increasing model performance through human expertise

   Författare :Niclas Ståhl; Göran Falkman; Alexander Karlsson; Gunnar Mathiason; Jonas Boström; Keith Downing; Högskolan i Skövde; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; INF301 Data Science; INF301 Data Science; Skövde Artificial Intelligence Lab SAIL ; Skövde Artificial Intelligence Lab SAIL ;

   Sammanfattning : The research in this thesis is focused on how deep learning models can be designed and implemented to better emulate and integrate the heuristic reasoning process of human experts. Several case studies, within the domains of steel making and drug discovery, are conducted in order to evaluate the performance of these models, in comparison to models that do not consider human expert knowledge from the targeted domain. LÄS MER

7. 25. 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