Results 61 to 70 of about 140,252 (207)

Comparison of DeePMD, MTP, GAP, ACE and MACE Machine‐Learned Potentials for Radiation‐Damage Simulations: A User Perspective

Advanced Intelligent Discovery, EarlyView.
The authors evaluated six machine‐learned interatomic potentials for simulating threshold displacement energies and tritium diffusion in LiAlO2 essential for tritium production. Trained on the same density functional theory data and benchmarked against traditional models for accuracy, stability, displacement energies, and cost, Moment Tensor Potential ...
Ankit Roy, Ram Devanathan, Sarah Allec, Giridhar Nandipati, Andrew M. Casella, David J. Senor, Duane D. Johnson, Ganesh Balasubramanian, Ayoub Soulami   +8 more
wiley   +1 more source

Cell Segmentation Beyond 2D—A Review of the State‐of‐the‐Art

Advanced Intelligent Discovery, EarlyView.
Cell segmentation underpins many biological image analysis tasks, yet most deep learning methods remain limited to 2D despite the inherently 3D nature of cellular processes. This review surveys segmentation approaches beyond 2D, comparing 2.5D and fully 3D methods, analyzing 31 models and 32 volumetric datasets, and introducing a unified reference ...
Fabian Schmeisser, Haseeb Muhammad, Junaid Younas, Gillian Lovell, Bianca Migliori, Andreas Dengel, Sheraz Ahmed   +6 more
wiley   +1 more source

Explaining the Origin of Negative Poisson's Ratio in Amorphous Networks With Machine Learning

Advanced Intelligent Discovery, EarlyView.
This review summarizes how machine learning (ML) breaks the “vicious cycle” in designing auxetic amorphous networks. By transitioning from traditional “black‐box” optimization to an interpretable “AI‐Physics” closed‐loop paradigm, ML is shown to not only discover highly optimized structures—such as all‐convex polygon networks—but also unveil hidden ...
Shengyu Lu, Xiangying Shen
wiley   +1 more source

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

Routing Optimization of Cable‐Driven Octopus‐Inspired Manipulators With Minimal Actuation via Genetic Algorithm and Finite Element Method

Advanced Intelligent Systems, EarlyView.
Soft robotic arms are promising for gentle grasping but often rely on bulky actuation systems. This work presents a computational design framework that optimizes tendon number and routing to achieve target grasps with fewer actuators. Validated on an octopus‐inspired underwater arm, the approach enables efficient, underactuated soft manipulators for ...
Michele Martini, Emanuele Solfiti, Alessio Mondini, Emanuela Del Dottore, Alberto Parmiggiani, Edoardo Sinibaldi, Barbara Mazzolai   +6 more
wiley   +1 more source

Geometry and categorification

, 2016
We describe a number of geometric contexts where categorification appears naturally: coherent sheaves, constructible sheaves and sheaves of modules over quantizations.
Webster, Ben
core  

i‐Tac: Inverse Design of 3D‐Printed Tactile Elastomers with Tuneable Optical and Mechanical Properties

Advanced Intelligent Systems, EarlyView.
Inspired by the multi‐tissue architecture of the human fingertip dermis (A), this work introduces a mixture design using three PolyJet materials (AC/TM/GM) to expand the achievable elastomer property space (B). An inverse design pipeline (i‐Tac) is developed to map target optical/mechanical requirements to optimal material compositions (C), enabling ...
Wen Fan, Dandan Zhang
wiley   +1 more source

Artificial Intelligence for Multiscale Modeling in Solid‐State Physics and Chemistry: A Comprehensive Review

Advanced Intelligent Systems, EarlyView.
This review explores the transformative impact of artificial intelligence on multiscale modeling in materials research. It highlights advancements such as machine learning force fields and graph neural networks, which enhance predictive capabilities while reducing computational costs in various applications.
Artem Maevskiy, Vitalii Kapitan, Andrey Ustyuzhanin   +2 more
wiley   +1 more source

MusicSwarm: Biologically Inspired Intelligence for Music Composition

Advanced Intelligent Systems, EarlyView.
Biologically inspired swarms of frozen foundation models self‐organize to compose complex music without fine‐tuning. By coordinating through stigmergic signals, decentralized agents dynamically evolve specialized roles and adapt to solve complex tasks.
Markus J. Buehler
wiley   +1 more source

Material‐Based Intelligence: Autonomous Adaptation and Embodied Computation in Physical Substrates

Advanced Intelligent Systems, EarlyView.
This perspective formulates a unifying framework for Material‐Based Intelligence (MBI), defining the physical requirements for materials to achieve embodied action, active memory and embodied information processing through intrinsic nonequilibrium dynamics. The design of intelligent materials often draws parallels with the complex adaptive behaviors of
Vladimir A. Baulin, Rudolf M. Füchslin, Achille Giacometti, Helmut Hauser, Marco Werner   +4 more
wiley   +1 more source