Sökning: "Kostnadsfunktion"
Visar resultat 1 - 5 av 27 uppsatser innehållade ordet Kostnadsfunktion.
1. Reinforcement Learning for Hydrobatic AUVs
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This master thesis focuses on developing a Reinforcement Learning (RL) controller to perform hydrobatic maneuvers on an Autonomous Underwater Vehicle (AUV) successfully. This work also aims to analyze the robustness of the RL controller, as well as provide a comparison between RL algorithms and Proportional Integral Derivative (PID) control. LÄS MER
2. Finite Control Set-Model Predictive control of Permanent Magnet Synchronous Motor
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The electrification of the transportation sector has been the most important goal of the current century. In the last decade, there has been a surge in the production and sale of electric vehicles, necessitating substantial research and development in the industry. LÄS MER
3. Using Symmetry for Realistic Virtual Living Room Generation : Generating virtual layouts
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Procedurell generering är en teknik som används inom dataspel och annan programvara för att generera innehåll algoritmiskt snarare än manuellt. I detta projekt utökas metoden av Kán och Kaufmann (2018) för att procedurellt generera trovärdiga, virtuella scenlayouter till att använda reflekterande symmetri för syntes [14]. LÄS MER
4. Developing A Network Algorithm for Demand Responsive Transit Service in A Rural Area of Sweden
Master-uppsats, KTH/TransportplaneringSammanfattning : Based on the fact that accessibility in rural areas relies heavily on car traffic, call-driven traffic has been used in different regions to improve public transport usage in rural areas, while it has been difficult to maintain due to high maintenance and long waiting time. Over the past decade, a new demand response transit (DRT) service came into light, which combines with new technologies to provide a more attractive and efficient transport service. LÄS MER
5. A General Approach to Inaudible Adversarial Perturbations in a Black-box Setting
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep learning is currently being deployed in many speech recognition systems. While these systems can achieve state-of-the-art performance, they are known to be susceptible to adversarial perturbations. These are minor perturbations to the input data, crafted specifically to cause erroneous behavior from the system. LÄS MER