Essays about: "overfitting"

Showing result 31 - 35 of 83 essays containing the word overfitting.

  1. 31. Convolutional neural network based object detection in a fish ladder : Positional and class imbalance problems using YOLOv3

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Patrik Ekman; [2021]
    Keywords : Object detection; Computer vision; Fish ladder; Imbalance problems; Imbalanced data; YOLO; Convolutional Neural Network; Deep learning; Objektdetektering; Datorseende; Fisktrappa; Obalanser; Obalanserad data; YOLO; Convolutional Neural Network; Djupinl¨arning;

    Abstract : Hydropower plants create blockages in fish migration routes. Fish ladders can serve as alternative routes but are complex to install and follow up to help adapt and develop them further. In this study, computer vision tools are considered in this regard. READ MORE

  3. 32. Single image scene-depth estimation based on self-supervised deep learning : For perception in autonomous heavy duty vehicles

    University essay from Uppsala universitet/Avdelningen för visuell information och interaktion

    Author : Yegor Piven; [2021]
    Keywords : computer vision; machine learning; deep learning; depth estimation; single image depth estimation;

    Abstract : Depth information is a vital component for perception of the 3D structure of vehicle's surroundings in the autonomous scenario. Ubiquity and relatively low cost of camera equipment make image-based depth estimation very attractive compared to employment of the specialised sensors. READ MORE

  4. 33. Choosing Only the Best Voice Imitators : Top-K Many-to-Many Voice Conversion with StarGAN-VC

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Claudio Fernandez Martin; [2021]
    Keywords : ;

    Abstract : Voice conversion systems are becoming more relevant as the popularity of voice technologies is growing with the increased adoption of voice assistants and the increased demand for speech-based interfaces in recent years. This scenario would not have been possible without the latest developments in the generative deep learning field, where novel neural networks architectures such as generative adversarial networks (GANs) are providing researchers with previously unimaginable possibilities in the creation of synthetic media. READ MORE

  5. 34. Optimization of Insert-Tray Matching using Machine Learning

    University essay from Uppsala universitet/Avdelningen för systemteknik

    Author : Karolina Hedberg; [2021]
    Keywords : Machine learning; Supervised learning; Feature selection;

    Abstract : The manufacturing process of carbide inserts at Sandvik Coromant consists of several operations. During some of these, the inserts are positioned on trays. For some inserts the trays are pre-defined but for others the insert-tray matching is partly improvised. READ MORE

  6. 35. Noise Reduction of Scintillation Camera Images Using UNET: A Monte Carlo Simulation Approach

    University essay from Lunds universitet/Sjukhusfysikerutbildningen

    Author : Johanna Korpijärvi; [2021]
    Keywords : Medicine and Health Sciences;

    Abstract : Background The project aims to reduce the noise in planar 111-In projections with a machine learning model. Method Sixteen base phantoms were used to create 696 phantoms in XCAT. An anterior planar projection was simulated with 111-In and ten uptake curves for each phantom in SIMIND. READ MORE