Sökning: "adversarial"
Visar resultat 1 - 5 av 56 avhandlingar innehållade ordet adversarial.
1. Sequential Data Learning, Scalable Models and Adversarial Regularization
Sammanfattning : Time Series Prediction (TSP) has been used in mobile network traffic data analysis to produce predictive results for network planning and resource allocation. In the first part of this thesis, we propose a novel method of predicting mobile network traffic using neural networks based on conditional probability modeling between adjacent data windows in the time series sequence. LÄS MER
2. Hidden Markov Models: Identification, Inverse Filtering and Applications
Sammanfattning : A hidden Markov model (HMM) comprises a state with Markovian dynamics that is hidden in the sense that it can only be observed via a noisy sensor. This thesis considers three themes in relation to HMMs, namely, identification, inverse filtering and applications. LÄS MER
3. Robust and Efficient Federated Learning for IoT Security
Sammanfattning : The widespread adoption of Internet of Things (IoT) devices has led to substantial progress across various industrial sectors, including healthcare, transportation, and manufacturing. However, these devices also introduce significant security vulnerabilities because they are often deployed without adequate security measures, making them susceptible to cyber threats. LÄS MER
4. Avtal om rätten till domstolsprövning. Processuella överenskommelsers giltighet i svensk rätt
Sammanfattning : One of the most fundamental rights in any democratic state is the right of access to court. Every individual shall have the right to bring legal disputes before a court, in a proceeding with specifically defined characteristics, a fair trial, and the state is responsible for supplying the conditions and prerequisites to carry out this dispute resolution process in a court of law. LÄS MER
5. Efficient Exploration and Robustness in Controlled Dynamical Systems
Sammanfattning : In this thesis, we explore two distinct topics. The first part of the thesis delves into efficient exploration in multi-task bandit models and model-free exploration in large Markov decision processes (MDPs). LÄS MER