Sökning: "black-box models"

Visar resultat 1 - 5 av 93 uppsatser innehållade orden black-box models.

1. 1. Computationally Efficient Explainable AI: Bayesian Optimization for Computing Multiple Counterfactual Explanantions

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Giorgio Sacchi; [2023]
   Nyckelord :Explainable AI; Counterfactual Explanations CFEs ; Bayesian Optimization BO ; Black-Box Models; Model-Agnostic; Machine Learning ML ; Efficient Computation; High-Stake Decisions; Förklarbar AI; Kontrafaktuell Förklaring CFE ; Bayesiansk Optimering BO ; Svarta lådmodeller; Modellagnostisk; Maskininlärning; Beräkningsmässigt Effektiv; Beslut med höga insatser;

   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

3. 2. Explainable Artificial Intelligence and its Applications in Behavioural Credit Scoring

   Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

   Författare :Robert Iain Salter; [2023]
   Nyckelord :Behavioural Credit Scoring; Deep Learning; Machine Learning; Long Short-Term Memory; Default Prediction;

   Sammanfattning : Credit scoring is critical for banks to evaluate new loan applications and monitor existing customers. Machine learning has been extensively researched for this case; however, the adoption of machine learning methods is minimal in financial risk management. LÄS MER

4. 3. Towards gradient faithfulness and beyond

   Master-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Vincenzo Buono; Isak Åkesson; [2023]
   Nyckelord :XAI; Visual Explanations; CAM; Grad-CAM; Expected Grad-CAM; Hyper Expected Grad; Class Activation Maps; Explainable AI; Faithfulness; Neural Network interpretability; Hyper Resolution CAM; Super Resolution CAM; Natural Encoding;

   Sammanfattning : The riveting interplay of industrialization, informalization, and exponential technological growth of recent years has shifted the attention from classical machine learning techniques to more sophisticated deep learning approaches; yet its intrinsic black-box nature has been impeding its widespread adoption in transparency-critical operations. In this rapidly evolving landscape, where the symbiotic relationship between research and practical applications has never been more interwoven, the contribution of this paper is twofold: advancing gradient faithfulness of CAM methods and exploring new frontiers beyond it. LÄS MER

5. 4. Increasing explainability of neural network based retail credit risk models

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Anton Evilevitch; [2023]
   Nyckelord :Explainability; Artificial Neural Network; Mortgage Credit Risk Modeling; Förklarbarhet; Artificiella Neurala Nätverk; Modellering av Hypotekskreditrisk;

   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

7. 5. Explainable modeling in machine learning : A comparative study

   Kandidat-uppsats, Umeå universitet/Statistik

   Författare :Simon Stålberg; Olivia Isaksson; [2023]
   Nyckelord :;

   Sammanfattning : As the use of advanced machine learning models has increased, the need for explainability that these models lack concerning their prediction has increased simultaneously. The aim of this thesis is to compare different functions available in the program R regarding their ability to provide explainability for these advanced machine learning models, also commonly referred to as black-box models. LÄS MER