Sökning: "Model-Agnostic"
Visar resultat 1 - 5 av 24 uppsatser innehållade ordet Model-Agnostic.
1. Neural Network-based Anomaly Detection Models and Interpretability Methods for Multivariate Time Series Data
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Anomaly detection plays a crucial role in various domains, such as transportation, cybersecurity, and industrial monitoring, where the timely identification of unusual patterns or outliers is of utmost importance. Traditional statistical techniques have limitations in handling complex and highdimensional data, which motivates the use of deep learning approaches. LÄS MER
2. Generating an Interpretable Ranking Model: Exploring the Power of Local Model-Agnostic Interpretability for Ranking Analysis
Magister-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Machine learning has revolutionized recommendation systems by employing ranking models for personalized item suggestions. However, the complexity of learning-to-rank (LTR) models poses challenges in understanding the underlying reasons contributing to the ranking outcomes. LÄS MER
3. Computationally Efficient Explainable AI: Bayesian Optimization for Computing Multiple Counterfactual Explanantions
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : In recent years, advanced machine learning (ML) models have revolutionized industries ranging from the healthcare sector to retail and E-commerce. However, these models have become increasingly complex, making it difficult for even domain experts to understand and retrace the model's decision-making process. LÄS MER
4. Real-time Energy Performance Tracking
Master-uppsats, Högskolan i Skövde/Institutionen för informationsteknologiSammanfattning : Energy performance tracking is becoming increasingly significant in the building industry as a means of improving energy efficiency. This thesis provides answers to the questions related to improving energy tracking system in general, including its potentials, problems and challenges. LÄS MER
5. Increasing explainability of neural network based retail credit risk models
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Due to their ’black box’ nature, Artificial Neural Networks (ANN) are not permitted for use in various applications. One such application is mortgage credit risk modeling. LÄS MER