Sökning: "shallow neural network"

Visar resultat 1 - 5 av 20 uppsatser innehållade orden shallow neural network.

1. 1. Estimation of Water Depth from Multispectral Drone Imagery : A suitability assessment of CNN models for bathymetry retrieval in shallow water areas

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Qianyao Shen; [2022]
   Nyckelord :Bathymetry Retrieval; Multispectral Imagery; Convolutional Neural Network CNN ; Hämtning Av Batymetri; Multispektrala Bilder; Konvolutionellt Neuralt Nätverk CNN ;

   Sammanfattning : Aedes aegypti and Aedes albopictus are the main vector species for dengue disease and zika, two arboviruses that affect a substantial fraction of the global population. These mosquitoes breed in very slow-moving or standing pools of water, so detecting and managing these potential breeding habitats is a crucial step in preventing the spread of these diseases. LÄS MER

3. 2. Combining Register Data and X-Ray Images for a Precision Medicine Prediction Model of Thigh Bone Fractures

   Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

   Författare :Alva Nilsson; Oliver Andlid; [2022]
   Nyckelord :AI; Machine Learning; Fusion; Classification; X-Ray Images; Register Data; EHR; Femoral Fractures; AFF; NFF; Transfer Learning;

   Sammanfattning : The purpose of this master thesis was to investigate if using both X-ray images and patient's register data could increase the performance of a neural network in discrimination of two types of fractures in the thigh bone, called atypical femoral fractures (AFF) and normal femoral fractures (NFF). We also examined and evaluated how the fusion of the two data types could be done and how different types of fusion affect the performance. LÄS MER

4. 3. The Dynamics of Neural Networks Expressivity with Applications to Remote Sensing Data

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Hui Zhang; [2022]
   Nyckelord :Neural Networks; Linear Regions; Expressivity; Initialization; Remote Sensing; Neurala nätverk; linjära regioner; uttrycksfullhet; initialisering; fjärranalys;

   Sammanfattning : Deep neural networks (DNN) have been widely demonstrated to be more powerful than their shallower counterparts in a variety of computer vision tasks and remote sensing applications. However, as many techniques are based on trial-and-error experiments as opposed to systematic evaluation, scientific evidence for the superiority of DNN needs more theoretical and experimental foundations. LÄS MER

5. 4. Skip connection in a MLP network for Parkinson’s classification

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Tim Steinholtz; [2021]
   Nyckelord :Parkinson’s Disease Classifications; Vocal Features; Multilayer Perceptron; DenseNet; Skip Connections; Highway Connections; Neural networks; Multiple Sound Types; Klassificering för Parkinsons sjukdom; MultiLayer Perceptron; Genvägs kopplingar; Röst attribut; DenseNet; Neurala Nätverk; Flertal Ljudkällor;

   Sammanfattning : In this thesis, two different architecture designs of a Multi-Layer Perceptron network have been implemented. One architecture being an ordinary MLP, and in the other adding DenseNet inspired skip connections to an MLP architecture. LÄS MER

7. 5. Normalization of Deep and Shallow CNNs tasked with Medical 3D PET-scans : Analysis of technique applicability

   Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Edlir Pllashniku; Zolal Stanikzai; [2021]
   Nyckelord :Machine learning; Deep learning; Neurology; Normalization; CNN; Deep neural network; Neurodegenerative disorders; Neurodegenerative disorders identification; Maskininlärning; Djup inlärning; Neurologi; Normalisering; CNN; Djupt neurala nätverk; Neurodegenerativa sjukdomar; Identifiering av neurodegenerativa sjukdomar;

   Sammanfattning : There has in recent years been interdisciplinary research on utilizing machine learning for detecting and classifying neurodegenerative disorders with the sole goal of outperforming state-of-the-art models in terms of metrics such as accuracy, specificity, and sensitivity. Specifically, these studies have been conducted using existing networks on ”novel” methods of pre-processing data or by developing new convolutional neural networks. LÄS MER