Explainable AI– tag –
-
Self-Driving Labs: Exploring the Feasibility of Closed-Loop Experimentation in Pharma R&D, Addressing XRD Data Challenges
Sakara Digital USA Overview This article discusses the feasibility of autonomous closed-loop experimentation in pharmaceutical R&D, identifying criteria for suitability and practical bottlenecks. The A-Lab team emphasizes demonstrati... -
Unveiling Physical Meaning in Materials AI: Beyond Prediction to Mechanism Identification and Design Guidance
ACS Materials Au USA Overview This perspective paper explores how materials AI can move beyond mere property prediction to contribute to physical interpretation, mechanism identification, and design guidance. It advocates for evaluating ... -
ACS Publications Establishes Data-Driven AI Design Framework for Mg-Sr-X Ternary Anodes in High-Performance Mg-Air Batteries
ACS Publications - Industrial & Engineering Chemistry Research USA Overview A paper in ACS Publications establishes an AI-driven alloy design framework for data-driven discovery of ternary anodes for high-performance Mg-air batteries. In... -
Explainable AI Unlocks Transparent Catalyst Design for Sustainable Technologies
ACS Applied Materials & Interfaces (ACS Publications) USA Overview A new review in ACS Applied Materials & Interfaces highlights the transformative potential of Explainable AI (XAI) in electrocatalysis and photocatalysis. The paper e... -
Tokyo Institute of Science Deciphers AI’s Material Property Predictions, Accelerating Design
東京科学大学 Japan Overview Researchers at Tokyo Institute of Science have developed an interpretable AI (XAI) methodology that reveals how AI models predict material properties, particularly light absorption spectra, from atomic structu... -
Tokyo Institute of Science Unveils Explainable AI Leveraging ALIGNN and Hierarchical Clustering for High-Accuracy Optical Spectra Prediction in Materials
HyperAI (via Google News) Japan Overview Researchers at the Tokyo Institute of Science have significantly enhanced the interpretability of AI-driven materials predictions by combining the ALIGNN graph neural network with hierarchical clu... -
Kyushu University Pioneers Explainable AI and ChatGPT-Powered ‘Human-in-the-Loop’ for Rapid AEM Material Discovery
九州大学ニュース Japan Overview Researchers at Kyushu University have developed a novel 'Human-in-the-Loop' framework that efficiently synthesizes explainable AI, ChatGPT, and expert human knowledge to accelerate the development of anion... -
Unlocking AI’s ‘Why’: Visualizing Prediction Rationale for Rapid Materials Discovery
不明 Japan Overview Researchers from Science Tokyo and Tohoku University have developed a novel interpretable AI (XAI) method that demystifies how AI models predict material properties. This breakthrough technique visualizes the intricat...
1