Chemical reaction networks and opportunities for machine learning
Chemical reaction networks (CRNs), defined by sets of species and possible reactions
between them, are widely used to interrogate chemical systems. To capture increasingly …
between them, are widely used to interrogate chemical systems. To capture increasingly …
Earthformer: Exploring space-time transformers for earth system forecasting
Conventionally, Earth system (eg, weather and climate) forecasting relies on numerical
simulation with complex physical models and hence is both expensive in computation and …
simulation with complex physical models and hence is both expensive in computation and …
Learning physical models that can respect conservation laws
D Hansen, DC Maddix, S Alizadeh… - International …, 2023 - proceedings.mlr.press
Recent work in scientific machine learning (SciML) has focused on incorporating partial
differential equation (PDE) information into the learning process. Much of this work has …
differential equation (PDE) information into the learning process. Much of this work has …
[HTML][HTML] Learning continuous models for continuous physics
Dynamical systems that evolve continuously over time are ubiquitous throughout science
and engineering. Machine learning (ML) provides data-driven approaches to model and …
and engineering. Machine learning (ML) provides data-driven approaches to model and …
A stochastic sequential quadratic optimization algorithm for nonlinear-equality-constrained optimization with rank-deficient Jacobians
A sequential quadratic optimization algorithm is proposed for solving smooth nonlinear-
equality-constrained optimization problems in which the objective function is defined by an …
equality-constrained optimization problems in which the objective function is defined by an …
Harnessing the power of neural operators with automatically encoded conservation laws
Neural operators (NOs) have emerged as effective tools for modeling complex physical
systems in scientific machine learning. In NOs, a central characteristic is to learn the …
systems in scientific machine learning. In NOs, a central characteristic is to learn the …
Superbench: A super-resolution benchmark dataset for scientific machine learning
Super-Resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of
finer details, and improving the overall quality and fidelity of the data representation. There is …
finer details, and improving the overall quality and fidelity of the data representation. There is …
A new computationally simple approach for implementing neural networks with output hard constraints
AV Konstantinov, LV Utkin - Doklady Mathematics, 2023 - Springer
A new computationally simple method of imposing hard convex constraints on the neural
network output values is proposed. The key idea is to map a latent vector to a point that is …
network output values is proposed. The key idea is to map a latent vector to a point that is …
Deep Learning for Optimization of Trajectories for Quadrotors
This letter presents a novel learning-based trajectory planning framework for quadrotors that
combines model-based optimization techniques with deep learning. Specifically, we …
combines model-based optimization techniques with deep learning. Specifically, we …
Neural fields with hard constraints of arbitrary differential order
While deep learning techniques have become extremely popular for solving a broad range
of optimization problems, methods to enforce hard constraints during optimization …
of optimization problems, methods to enforce hard constraints during optimization …