Sökning: "black box model interpretability"

Visar resultat 1 - 5 av 13 uppsatser innehållade orden black box model interpretability.

1. 1. Developing a highly accurate, locally interpretable neural network for medical image analysis

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

   Författare :Rony David Ventura Caballero; [2023]
   Nyckelord :XAI; Interpretability; Computer vision; Pediatric pneumonia; Chest radiograph;

   Sammanfattning : Background Machine learning techniques, such as convolutional networks, have shown promise in medical image analysis, including the detection of pediatric pneumonia. However, the interpretability of these models is often lacking, compromising their trustworthiness and acceptance in medical applications. LÄS MER

3. 2. GAN-Based Counterfactual Explanation on Images

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

   Författare :Ning Wang; [2023]
   Nyckelord :: Machine Learning; Counterfactual Explanation; GAN; DCGAN;

   Sammanfattning : Machine learning models are widely used in various industries. However, the black-box nature of the model limits users’ understanding and trust in its inner workings, and the interpretability of the model becomes critical. LÄS MER

4. 3. Explainable AI by Training Introspection

   Master-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Rozhin Dastkarvelayati; Soudabeh Ghafourian; [2023]
   Nyckelord :Explainable Artificial Intelligence XAI ; Model Improvement; XAI stability;

   Sammanfattning : Deep Neural Networks (DNNs) are known as black box algorithmsthat lack transparency and interpretability for humans. eXplainableArtificial Intelligence (XAI) is introduced to tackle this problem. MostXAI methods are utilized post-training, providing explanations of themodel to clarify its predictions and inner workings for human understanding. LÄS MER

5. 4. Explainable Reinforcement Learning for Gameplay

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

   Författare :Àlex Costa Sánchez; [2022]
   Nyckelord :Explainable Artificial Intelligence; Local Interpretable Model-agnostic Explanations; Reinforcement Learning; Shapley Additive Explanations; Intel·ligencia Artificial Interpretable; Explicacions model-agnòstiques localment interpretables; Aprenentatge per reforç; Explicacions additives de Shapley; Förklarbar artificiell intelligent; Lokala tolkningsbara modellagnostiska förklaringar; Förstärkningsinlärning; Shapleys additiv förklaringar;

   Sammanfattning : 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. LÄS MER

7. 5. Survivability Prediction and Analysis using Interpretable Machine Learning : A Study on Protecting Ships in Naval Electronic Warfare

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Sidney Rydström; [2022]
   Nyckelord :Electronic warfare; machine learning; statistics; Artificial Neural Networks; ANN; multi-layer perceptron; multi-task learning; interpretable machine learning; Shapley values; kernel SHAP;

   Sammanfattning : Computer simulation is a commonly applied technique for studying electronic warfare duels. This thesis aims to apply machine learning techniques to convert simulation output data into knowledge and insights regarding defensive actions for a ship facing multiple hostile missiles. LÄS MER