Machine Learning and Knowledge Extraction

TRAMA

This volume LNCS-IFIP constitutes the refereed proceedings of the 7th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2023 in Benevento, Italy, during August 28 – September 1, 2023.  The 18 full papers presented together were carefully reviewed and selected from 30 submissions. The conference focuses on integrative machine learning approach, considering the importance of data science and visualization for the algorithmic pipeline with a strong emphasis on privacy, data protection, safety and security.

SOMMARIO

Controllable AI - An alternative to trustworthiness in complex AI systems?.- Efficient approximation of Asymmetric Shapley Values using Functional Decomposition.- Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition.- Human-in-the-Loop Integration of Domain-Knowledge Graphs for Explainable and Federated Deep Learning.- The Tower of Babel in explainable Artificial Intelligence (XAI).- Hyper-Stacked: Scalable and Distributed Approach to AutoML for Big Data.- Transformers are Short-text Classifiers.- Reinforcement Learning with Temporal-Logic-Based Causal Diagrams.- Using Machine Learning to Generate an ESG Dictionary.- Let me think! Investigating the effect of explanations feeding doubts about the AI advice.- Enhancing Trust in Machine Learning Systems by Formal Methods.- Sustainability Effects of Robust and Resilient Artificial Intelligence.- The Split Matters: Flat Minima Methods for Improving the Performance of GNNs.- Probabilistic framework based on Deep Learning for differentiating ultrasound movie view planes.- Standing Still is Not An Option: Alternative Baselines for Attainable Utility Preservation.- Memorization of Named Entities in Fine-tuned BERT Models.- Event and Entity Extraction from Generated Video Captions.- Fine-Tuning Language Models for Scientific Writing Support.

ALTRE INFORMAZIONI

• Condizione: Nuovo
• ISBN: 9783031408366
• Collana: Lecture Notes in Computer Science
• Dimensioni: 235 x 155 mm Ø 516 gr
• Formato: Brossura
• Illustration Notes: XV, 320 p. 64 illus., 53 illus. in color.
• Pagine Arabe: 320
• Pagine Romane: xv