Search Results for author:
Found 8 papers, 2 papers with code
Data-Driven Discovery of PDEs via the Adjoint Method
In particular, for a family of parameterized and nonlinear PDEs, we show how the corresponding adjoint equations can be derived.
Enhanced Human-Robot Collaboration using Constrained Probabilistic Human-Motion Prediction
We propose a novel human motion prediction framework that incorporates human joint constraints and scene constraints in a Gaussian Process Regression (GPR) model to predict human motion over a set time horizon.
MESSY Estimation: Maximum-Entropy based Stochastic and Symbolic densitY Estimation
We validate the proposed MESSY estimation method against other benchmark methods for the case of a bi-modal and a discontinuous density, as well as a density at the limit of physical realizability.
GSR: A Generalized Symbolic Regression Approach
Identifying the mathematical relationships that best describe a dataset remains a very challenging problem in machine learning, and is known as Symbolic Regression (SR).
Reliable Neural Networks for Regression Uncertainty Estimation
While deep neural networks are highly performant and successful in a wide range of real-world problems, estimating their predictive uncertainty remains a challenging task.
D-DARTS: Distributed Differentiable Architecture Search
This approach is accompanied by a novel metric that measures the distance between architectures inside our custom search space.
Instance Semantic Segmentation Benefits from Generative Adversarial Networks
Rethinking reconstruction networks as a generator, we define the problem of predicting masks as a GANs game framework: A segmentation network generates the masks, and a discriminator network decides on the quality of the masks.
Cyclic Graph Dynamic Multilayer Perceptron for Periodic Signals
However, it is difficult to perfectly control the collection timing of the measurements.
