AIPOCH Network
Find a direction, understand the work, and discover what you can build on.
DeepChem is a scientific machine-learning library with utilities for datasets, feature processing, splitting and model evaluation. Molecular learning is one documented application within its broader scientific scope.
Formulate and solve finite-element problems using the C++ and Python environment at the core of FEniCSx.
Describe and numerically solve rational-expectations economic models, including models with occasionally binding constraints.
Estimate and infer target parameters in specified causal models using double/debiased machine learning; identification assumptions remain the researcher's responsibility.
Model robotics systems for contact simulation, optimization, planning and control.
Generate atomistic descriptors and derivatives for materials modeling and machine learning.
Model crop growth, yield and soil–plant–atmosphere processes with the DSSAT cropping system model.
Estimate posterior distributions and Bayesian evidence with dynamic nested sampling.
Catalog snapshot 2026-09-22. Date ranges use UTC. Filters use the captured page time; results can change with a new catalog snapshot. Research stays at its original source.