Results 221 to 230 of about 630,172 (279)

Spheres, tears, and spears: Regulating the perimeter and circularity of millimeter‐sized alginate hydrogel beads

AIChE Journal, EarlyView.
Abstract Generating hydrogel beads pertains to many engineering applications. We examined two alginate‐based fluids at three concentrations of alginate, cAG$$ {c}_{\mathrm{AG}} $$. We used the “Map of Misery” to determine which material property (viscosity, elasticity, and inertia) drives droplet formation.
Conor G. Harris, Katherine D. Bandettini, Hannah K. Gedde, Lewis Semprini, Kaitlin C. Fogg, Willie E. Rochefort   +5 more
wiley   +1 more source

A variational framework for residual-based adaptivity in neural PDE solvers and operator learning. [PDF]

NPJ Artif Intell
Toscano JD, Chen DT, Ooomen V, Darbon J, Karniadakis GE.   +4 more
europepmc   +1 more source

Graph‐based imitation and reinforcement learning for efficient Benders decomposition

AIChE Journal, EarlyView.
Abstract This work introduces an end‐to‐end graph‐based agent for accelerating the computational efficiency of Benders Decomposition. The agent's policy is parameterized by a graph neural network, which takes as input a bipartite graph representation of the master problem and proposes a candidate solution.
Bernard T. Agyeman, Zhe Li, Ilias Mitrai, Prodromos Daoutidis   +3 more
wiley   +1 more source

Quantifying the honey bee dance floor: A data-driven method for defining and comparing waggle dance regions. [PDF]

PLoS One
Van Nest BN, Wagner AE, Joyner ML, Seier E, Moore D.   +4 more
europepmc   +1 more source

Universally Accurate or Specifically Inadequate? Stress‐Testing General Purpose Machine Learning Interatomic Potentials

Advanced Intelligent Discovery, EarlyView.
We investigate MACE‐MP‐0 and M3GNet, two general‐purpose machine learning potentials, in materials discovery and find that both generally yield reliable predictions. At the same time, both potentials show a bias towards overstabilizing high energy metastable states. We deduce a metric to quantify when these potentials are safe to use.
Konstantin S. Jakob, Karsten Reuter, Johannes T. Margraf   +2 more
wiley   +1 more source

Linear Causal Discovery with Interventional Constraints. [PDF]

Mach Learn
Guo Z, Dong F.
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

Modified prioritized DDPG algorithm for joint beamforming and RIS phase optimization in MISO downlink systems. [PDF]

Sci Rep
Shukry S, Fahmy Y.
europepmc   +1 more source

Interior Point-Driven Throughput Maximization for TS-SWIPT Multi-Hop DF Relays: A Log Barrier Approach. [PDF]

Sensors (Basel)
Yu Y, Tang X, Xie G.
europepmc   +1 more source

Convex Hartree-Fock theory for modeling ground state conical intersections. [PDF]

Commun Chem
Rossi F, Koch H.
europepmc   +1 more source