An overview of the recent developments of time-series neural network modeling is presented along with its use in model predictive control (MPC). A tutorial on the construction …
It is widely known that neural networks (NNs) are universal approximators of continuous functions. However, a less known but powerful result is that a NN with a single hidden layer …
P Kidger - arXiv preprint arXiv:2202.02435, 2022 - arxiv.org
The conjoining of dynamical systems and deep learning has become a topic of great interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …
Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …
In the context of science, the well-known adage" a picture is worth a thousand words" might well be" a model is worth a thousand datasets." In this manuscript we introduce the SciML …
While it is widely known that neural networks are universal approximators of continuous functions, a less known and perhaps more powerful result is that a neural network with a …
RTQ Chen, Y Rubanova… - Advances in neural …, 2018 - proceedings.neurips.cc
We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a …
M Raissi - Journal of Machine Learning Research, 2018 - jmlr.org
We put forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time. Specifically …
K Champion, B Lusch, JN Kutz… - Proceedings of the …, 2019 - National Acad Sciences
The discovery of governing equations from scientific data has the potential to transform data- rich fields that lack well-characterized quantitative descriptions. Advances in sparse …