Results 71 to 80 of about 128 (127)
Harnessing Machine Learning to Understand and Design Disordered Solids
Advanced Intelligent Discovery, EarlyView.This review maps the dynamic evolution of machine learning in disordered solids, from structural representations to generative modeling. It explores how deep learning and model explainability transform property prediction into profound physical insight.
Muchen Wang, Yue Fan
wiley +1 more source
Large‐Scale Machine Learning to Screen for Small‐Molecule Senolytics
Advanced Intelligent Discovery, EarlyView.A consistent workflow underpins all experiments in this study. A dedicated model‐selection dataset first identifies optimal hyperparameters for each algorithm. Models are then trained and rigorously evaluated on independent sets of molecules using the senolytic ratio SR. Comprehensive hyperparameter exploration across SMILES representations, task types,
Alexis Dougha +2 more
wiley +1 more source
MolMiner: Toward Controllable, Three‐Dimensional‐Aware, Fragment‐Based Molecular Design
Advanced Intelligent Discovery, EarlyView.MolMiner is a fragment‐based, geometry‐aware, and order‐agnostic generative model for molecular design with strong inductive biases. Using symmetry‐aware fragment assembly, dynamic three‐dimensional geometry, and multi‐property conditioning, MolMiner enables interpretable and controllable molecular generation.
Raul Ortega‐Ochoa +2 more
wiley +1 more source
A Language‐Guided Multimodal Foundation Model for Zero‐Shot and Multi‐Task Brain Signal Analysis
Advanced Intelligent Systems, EarlyView.METIS aligns brain signals with natural‐language instructions to enable zero‐shot and multi‐task brain signal analysis. Pretrained on over 70 000 h of EEG and iEEG recordings, it generalizes across sleep stage classification, epilepsy detection, and neurological disorder diagnosis, providing a scalable foundation model for clinically meaningful brain ...
Mingzhi Chen +3 more
wiley +1 more source
Artificial Intelligence for Advanced Functional Materials: Progress and Emerging Frontiers
Advanced Intelligent Systems, EarlyView.Artificial intelligence is transforming the discovery of functional materials by linking synthesis, characterization, simulation, and design in unified workflows. Advances in machine learning, autonomous experimentation, and foundation models are accelerating innovation across energy, electronics, and biomedicine, while revealing new frontiers for ...
Cristiano Malica +38 more
wiley +1 more source
Advanced Intelligent Systems, EarlyView.This study introduces Cellular Material Network (CM‐Net), a pioneering machine learning architecture integrating physical information, to predict the mechanical properties of cellular materials. Comprehensive validation through simulations and experiments demonstrates its accuracy in predicting nonlinear behaviors, including initial peak compression ...
Sicong Zhou +5 more
wiley +1 more source
Angewandte Chemie, EarlyView.LiMn2O4${\rm LiMn}_2{\rm O}_4$ is of high interest for sustainable energy storage and conversion. Its mixed‐valence Mn3+${\rm Mn}^{3+}$/Mn4+${\text{Mn}}^{4+}$ structure drives site‐specific behavior at aqueous interfaces, featuring proton‐generating Mn4+${\text{Mn}}^{4+}$ centers and electron‐rich Mn3+${\rm Mn}^{3+}$ sites that render the surrounding ...
K. Nikolas Lausch +3 more
wiley +2 more sources
Comparative Analysis of Model‐Agnostic Explanation Methods in Materials Science
Advanced Intelligent Systems, EarlyView.To address the critical lack of explainable artificial intelligence (XAI) benchmarks in materials science, we present a quantitative and qualitative analysis of six XAI methods applied to molecular fingerprints. Our results reveal significant discrepancies in feature importance rankings, demonstrating that the chosen explanation approach introduces ...
Anna Przybyłowska +7 more
wiley +1 more source
A Scalable and Resource‐Efficient Pipelined p‐Computer for Probabilistic Ising Machines
Advanced Intelligent Systems, EarlyView.(a) Block diagram of the portfolio optimization problem: given M assets, the goal is to determine the optimal weights w that maximize the expected return (based on the mean historical assets return u), while minimizing the risk, quantified by the assets covariance matrix S.
Deborah Volpe +9 more
wiley +1 more source
Exploiting Edge Semantics in Job Shop Scheduling Problem With Heterogeneous Graph Transformers
Advanced Intelligent Systems, EarlyView.A heterogeneous graph transformer (HGT) is introduced for reinforcement learning‐based job shop scheduling by explicitly distinguishing precedence and machine‐contention relations through edge‐type‐specific attention. The proposed framework learns richer scheduling representations, improves decision quality over homogeneous graph models, and highlights
Bulent Soykan, Fatih Kasimoglu
wiley +1 more source