Sökning: "Adversarial Machine Learning"
Visar resultat 1 - 5 av 109 uppsatser innehållade orden Adversarial Machine Learning.
1. Restaurant Daily Revenue Prediction : Utilizing Synthetic Time Series Data for Improved Model Performance
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för beräkningsvetenskapSammanfattning : This study aims to enhance the accuracy of a demand forecasting model, XGBoost, by incorporating synthetic multivariate restaurant time series data during the training process. The research addresses the limited availability of training data by generating synthetic data using TimeGAN, a generative adversarial deep neural network tailored for time series data. LÄS MER
2. Using Synthetic Data to ModelMobile User Interface Interactions
Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)Sammanfattning : Usability testing within User Interface (UI) is a central part of assuring high-quality UIdesign that provides good user-experiences across multiple user-groups. The processof usability testing often times requires extensive collection of user feedback, preferablyacross multiple user groups, to ensure an unbiased observation of the potential designflaws within the UI design. LÄS MER
3. Adversarial robustness of STDP-trained spiking neural networks
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Adversarial attacks on machine learning models are designed to elicit the wrong behavior from the model. One such attack on image classifiers are maliciously crafted inputs that, to the human eye, look untampered with but have been carefully altered to cause misclassification. LÄS MER
4. Adversarial Machine (Deep) Learning-basedRobustification in 5G Networks
Master-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : A significant development in wireless communication and artificial intelligence has been made possible by the combination of 5G networks with deep learning methods. This paper explores the complex interactions between these areas, concentrating on the dangers that adversarial attacks represent in the context of 5G network slicing. LÄS MER
5. Using Generative Adversarial Networks for H&E-to-HER2 Stain Translation in Digital Pathology Images
Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknikSammanfattning : In digital pathology, hematoxylin & eosin (H&E) is a routine stain which is performed on most clinical cases and it often provides clinicians with sufficient information for diagnosis. However, when making decisions on how to guide breast cancer treatment, immunohistochemical staining of human epidermal growth factor 2 (HER2 staining) is also needed. LÄS MER