Essays about: "Local Interpretable Model-Agnostic Explanations LIME"
Showing result 1 - 5 of 12 essays containing the words Local Interpretable Model-Agnostic Explanations LIME.
-
1. Generating an Interpretable Ranking Model: Exploring the Power of Local Model-Agnostic Interpretability for Ranking Analysis
University essay from Stockholms universitet/Institutionen för data- och systemvetenskapAbstract : 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. READ MORE
-
2. Real-time Energy Performance Tracking
University essay from Högskolan i Skövde/Institutionen för informationsteknologiAbstract : 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. READ MORE
-
3. Increasing explainability of neural network based retail credit risk models
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
4. Evolutionary Belief Rule based Explainable AI to Predict Air Pollution
University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknikAbstract : This thesis presents a novel approach to make Artificial Intelligence (AI) more explainable by using a Belief Rule Based Expert System (BRBES). A BRBES is a type of expert system that can handle both qualitative and quantitative information under uncertainty and incompleteness by using if-then rules with belief degrees. READ MORE
-
5. Explainable Reinforcement Learning for Gameplay
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : State-of-the-art Machine Learning (ML) algorithms show impressive results for a myriad of applications. However, they operate as a sort of a black box: the decisions taken are not human-understandable. READ MORE