The text focuses on the methodologies of generative artificial intelligence, and explainable artificial intelligence, providing readers with an understanding of how artificial intelligence models can be transparent and interpretable. It explores various XAI techniques, feature importance, SHAP values, LIME, and counterfactual explanations.
Inhaltsverzeichnis
1. Decoding GenAI: An Introduction to Transformers 2. Bridging the Gap: Integrating Generative AI and Explainability 3. XAI decoded: A systematic literature review on Explainability 4. Applications of Explainable Artificial Intelligence in Healthcare 5. Interactive UI for Captum: Enhancing Explainable AI Accessibility 6. Filling the AI Data Void: Synthesizing Domain-Specific Knowledge using Generative AI 7. Generating Synthetic Images in Multi-Agent Cooperating Environment Focusing on Generalizability 8. Exploring Diffusion Models: Techniques, Applications, and Future Directions 9. Multimodal Generative AI in Healthcare: A Comprehensive Review of Models and Applications 10. Comparative Analysis of Convolutional Neural Network Architectures for Diabetic Retinopathy Classification and Grading in Retinal Images Using Generative AI and Explainable AI 11. From Steps to Signals: Machine Learning for Explainable Gait Analysis 12. A Study on Deep Learning and Machine Learning Methods for Automated Brain Hemorrhage Detection 13. GenAIED: GenAI in Education 14. Generative Intelligence Meets Precision Farming: A Hybrid CNN-RAG Approach for Early Plant Disease Management 15. Applications of Generative AI in Education: A Conceptual Framework for Ethical Implementation in Higher Education Curricula 16. AI in Industry 5.0: Future Trends, Green AI, and Accountability 17. Exploring Multimodal AI Applications in Healthcare, Smart Homes, Autonomous Vehicles, and Speech Recognition