Results 231 to 240 of about 12,004,986 (327)

Decoding Tattoo and Permanent Makeup Pigments: Linking Physicochemical Properties to Absorption, Distribution, Metabolism, and Elimination Profiles Using Quantitative Structure–Activity Relationship (QSAR)‐Based New Approach Methodologies (NAMs)

Advanced Intelligent Discovery, EarlyView.
This study applies QSAR‐based new approach methodologies to 90 synthetic tattoo and permanent makeup pigments, revealing systemic links between their physicochemical properties and absorption, distribution, metabolism, and elimination profiles. The correlation‐driven analysis using SwissADME, ChemBCPP, and principal component analysis uncovers insights
Girija Bansod, Ajay Vikram Singh, Preeti Bhardwaj, Tulika Rai, Sweta Vijay Nakhale, Amruta Shelar, Rajendra Patil, Peter Laux, Andreas Luch, Christopher J. Osgood, Michael W. Stacey   +10 more
wiley   +1 more source

Interactive imitation learning for dexterous robotic manipulation: challenges and perspectives-a survey. [PDF]

Front Robot AI
Welte E, Rayyes R.
europepmc   +1 more source

What to Make and How to Make It: Combining Machine Learning and Statistical Learning to Design New Materials

Advanced Intelligent Discovery, EarlyView.
Combining machine learning and probabilistic statistical learning is a powerful way to discover and design new materials. A variety of machine learning approaches can be used to identify promising candidates for target applications, and causal inference can help identify potential ways to make them a reality.
Jonathan Y. C. Ting, Amanda S. Barnard
wiley   +1 more source

LG-H-PPO: offline hierarchical PPO for robot path planning on a latent graph. [PDF]

Front Robot AI
Han X.
europepmc   +1 more source

The Necessity of Dynamic Workflow Managers for Advancing Self‐Driving Labs and Optimizers

Advanced Intelligent Discovery, EarlyView.
We assess the maturity and integration readiness of key methodologies for Materials Acceleration Platforms, highlighting the need for dynamic workflow managers. Demonstrating this, we integrate PerQueue into a color‐mixing robot, showing how flexible orchestration improves coordination and optimization.
Simon K. Steensen, Patrick W. V. Butler, Jesper R. Pedersen, Nis Fisker‐Bødker, Tejs Vegge, Jin Hyun Chang, Ivano E. Castelli   +6 more
wiley   +1 more source

Model-free optical processors using in situ reinforcement learning with proximal policy optimization. [PDF]

Light Sci Appl
Li Y, Chen S, Gong T, Ozcan A.
europepmc   +1 more source

Large Language Model in Materials Science: Roles, Challenges, and Strategic Outlook

Advanced Intelligent Discovery, EarlyView.
Large language models (LLMs) are reshaping materials science. Acting as Oracle, Surrogate, Quant, and Arbiter, they now extract knowledge, predict properties, gauge risk, and steer decisions within a traceable loop. Overcoming data heterogeneity, hallucinations, and poor interpretability demands domain‐adapted models, cross‐modal data standards, and ...
Jinglan Zhang, Xinyi Chen, Xu Ye, Yulin Yang, Bin Ai   +4 more
wiley   +1 more source

Health state prediction with reinforcement learning for predictive maintenance. [PDF]

Front Artif Intell
Aglogallos A, Bousdekis A, Kontos S, Mentzas G.   +3 more
europepmc   +1 more source

Advanced Experiment Design Strategies for Drug Development

Advanced Intelligent Discovery, EarlyView.
Wang et al. analyze 592 drug development studies published between 2020 and 2024 that applied design of experiments methodologies. The review surveys both classical and emerging approaches—including Bayesian optimization and active learning—and identifies a critical gap between advanced experimental strategies and their practical adoption in ...
Fanjin Wang, Anthony Harker, Mohan Edirisinghe, Maryam Parhizkar   +3 more
wiley   +1 more source

Adaptive motion planning for legged robots in unstructured terrain using deep reinforcement learning. [PDF]

Sci Rep
Uddin MS.
europepmc   +1 more source