Sökning: "Deep Learning"
Visar resultat 1 - 5 av 1981 uppsatser innehållade orden Deep Learning.
1. 100 år av representativ demokrati - Hur har våra ”blivande ministrars” bakgrund förändrats under denna tid?
Kandidat-uppsats,Sammanfattning : Background, objectives, earlier research, and method The Swedish parliament approved universal and equal suffrage for women and men on 24 May 1919. The election to the Swedish second chamber in the parliament in fall 2021 was the first election according to the new regulations. It has now past more than 100 years since this reform. LÄS MER
2. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. LÄS MER
3. Machine learning for molecular property prediction and drug safety
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Utilizing machine learning methods for the prediction of acid dissociation (pKa ) values of compounds holds great significance, as pKa is an important parameter, optimized frequently in drug discovery. Accurate prediction of pKa values could potentially provide valuable insights on other molecular properties and thereby support compound design. LÄS MER
4. Improving echocardiogram view classification using diffusion models
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : In the field of medical science datasets are often highly imbalanced, where rare datapoints are of high importance. This study aims to explore the usage of synthetic datasets to improve the classification of echocardiogram views. LÄS MER
5. Despeckling Echocardiograms Using Generative Adversarial Networks
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Previous research had shown that generative adversarial networks (GANs) are capable of despeckling echocardiograms (echos) through image-to-image translation in real-time once trained. However, only limited information regarding the quality of denoised echos and explainability of useful GAN components is provided. LÄS MER
