Sökning: "Black-box models"
Visar resultat 1 - 5 av 54 avhandlingar innehållade orden Black-box models.
1. Recursive black-box identification of nonlinear state-space ODE models
Sammanfattning : Nonlinear system identification methods is a topic that has been gaining interest over the last years. One reason is the many application areas in controller design and system development. However, the problem of modeling nonlinear systems is complex and finding a general method that can be used for many different applications is difficult. LÄS MER
2. Context-based explanations for machine learning predictions
Sammanfattning : In recent years, growing concern regarding trust in algorithmic decision-making has drawn attention to more transparent and interpretable models. Laws and regulations are moving towards requiring this functionality from information systems to prevent unintended side effects. LÄS MER
3. Demystifying the Black Box - Exploring How Users Make Sense of Fully Automated Vehicles
Sammanfattning : Vehicles are becoming increasingly automated. Already today vehicles are able to take over and assist the human driver in certain driving tasks, and the scope of technical possibilities is rapidly expanding. However, for the proliferation of AVs to occur, there are several challenges that must first be overcome. LÄS MER
4. Inside the black box of workplace interventions : investigating the influence of context and process on outcomes
Sammanfattning : Introduction: Staff working in healthcare and residential care for older people are continuously required to learn and develop competencies to keep up with medical, technological and social developments. At the same time, they experience a work situation generally characterized by high demands. LÄS MER
5. Methods for Frequency Domain Estimation of Continuous-Time Models
Sammanfattning : Approaching parameter estimation from the discrete-time domain is the dominating paradigm in system identification. Identification of continuous-time models on the other hand is motivated by the fact that modelling of physical systems often take place in continuous-time. LÄS MER