Sökning: "Hyperparametrar"

Visar resultat 1 - 5 av 69 uppsatser innehållade ordet Hyperparametrar.

  1. 1. Robust Portfolio Optimization with Correlation Penalties

    Master-uppsats, KTH/Matematisk statistik

    Författare :Pelle Nydahl; [2023]
    Nyckelord :Portfolio Optimization; Portfolio Allocation; Robust Optimization; Correlation; Risk Factor Model; EMA Filtering; Weighted Linear Regression; Portföljoptimering; Portföljallokering; Robust optimering; Korrelation; Riskfaktor-modell; EMA-filtrering; Viktad linjär regression;

    Sammanfattning : Robust portfolio optimization models attempt to address the standard optimization method's high sensitivity to noise in the parameter estimates, by taking an investor's uncertainty about the estimates into account when finding an optimal portfolio. In this thesis, we study robust variations of an extension of the mean-variance problem, where an additional term penalizing the portfolio's correlation with an exogenous return sequence is included in the objective. LÄS MER

  3. 2. Comparing energy efficiency of Leaky integrate-and-fire and Spike response neuron models in Spiking Neural Networks

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

    Författare :Majd Dawli; Imran Bahed Diva; [2023]
    Nyckelord :;

    Sammanfattning : Spiking Neural Networks (SNNs) are a type of neural network that is designed to mimic the way neurons function in our brains. While there have been notable advancements in developing SNNs, energy consumption hasn't been studied to the same extent. This gets especially relevant with steadily increasing network sizes. LÄS MER

  4. 3. Deep Reinforcement Learning in Games Based on Extracted Features

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

    Författare :Emilia Sjögren; Erika Weidenhaijn; [2023]
    Nyckelord :;

    Sammanfattning : FlappyBird is a popular mobile game that captured many people's attention because itwas easy to understand but difficult to perform --- players were often right on the edge ofsucceeding, which led to a strong desire to play again. The purpose of this project is to investigatethe possibility of using a neural network trained with reinforcement learning to play the game usingextracted features rather than raw images. LÄS MER

  5. 4. Prediction Models for TV Case Resolution Times with Machine Learning

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

    Författare :Borja Javierre I Moyano; [2023]
    Nyckelord :Datasets; Machine Learning ML ; Prediction; Resolution Time RT ; Solve Time; TV Cases; Trouble Tickets TT ; Customer-Related Trouble Tickets Resolution Time; CRM system; BI system; Telecommunications; Dataset; Machine Learning ML ; Prediction; Resolution Time; Solve Time; TV Cases; Trouble Tickets TT ; Kundrelaterade problem Tickets Resolution tid; CRM-system; BI-system; Telekommunikationer.;

    Sammanfattning : TV distribution and stream content delivery of video over the Internet, since is made up of complex networks including Content Delivery Networks (CDNs), cables and end-point user devices, that is very prone to issues appearing in different levels of the network ending up affecting the final customer’s TV services. When a problem affects the customer, and this prevents from having a proper TV delivery service in devices used for stream purposes, the issue is reported through a call, a TV case is opened and the company’s customer handling agents start supervising it to solve the problem as soon as possible. LÄS MER

  7. 5. Accuracy and Robustness of State of the Art Deepfake Detection Models

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

    Författare :Tobias Carlsson; Oskar Strömberg; [2023]
    Nyckelord :;

    Sammanfattning : With the evolution of artificial intelligence a lot of people have started getting worried about the potential dangers of deepfake images and videos, such as spreading fake videos of influential people. Several solutions to this problem have been proposed with some of the most efficient being convolutional neural networks for face detection in order to differentiate real images from deepfake images generated with a generative adversarial network. LÄS MER