Sökning: "Syntetisk datamängd"

Hittade 3 uppsatser innehållade orden Syntetisk datamängd.

  1. 1. Generating Extreme Value Distributions in Finance using Generative Adversarial Networks

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :William Nord-Nilsson; [2023]
    Nyckelord :Extreme Value Theory; Generative Adversarial Networks; Stress Testing; Machine Learning; Convolutional Neural Networks; evtGAN; Extreme Events; Extremvärdesteori; Generativa nätverk; Stresstestning; Maskininlärning; Djupt neuralt nätverk; evtGAN; Extrema händelser;

    Sammanfattning : This thesis aims to develop a new model for stress-testing financial portfolios using Extreme Value Theory (EVT) and General Adversarial Networks (GANs). The current practice of risk management relies on mathematical or historical models, such as Value-at-Risk and expected shortfall. LÄS MER

  3. 2. Enforcing low confidence class predictions for out of distribution data in deep convolutional networks

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

    Författare :Luca Marson; [2020]
    Nyckelord :;

    Sammanfattning : Modern discriminative deep neural networks are known to perform high confident predictions for inputs far away from the training data distribution, commonly referred to as out-of-distribution inputs. This property poses security concerns for the deployment of deep learning models in critical applications like autonomous vehicles because it hinders the detection of such inputs. LÄS MER

  4. 3. An empirical study on synthetic image generation techniques for object detectors

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

    Författare :Claudio Salvatore Arcidiacono; [2018]
    Nyckelord :Object Detection; Synthetic Dataset; Deep Learning; Rendered Images; Computer Vision; Objektdetektion; Syntetisk datamängd; Djup inlärning; Återgivna bilder; Datorseende;

    Sammanfattning : Convolutional Neural Networks are a very powerful machine learning tool that outperformed other techniques in image recognition tasks. The biggest drawback of this method is the massive amount of training data required, since producing training data for image recognition tasks is very labor intensive. LÄS MER