15 citations · 43 across the 12 of their papers we have counts for
12 papers
DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning
Shunxin Wang, Christoph Brune, Raymond Veldhuis +1
Neural networks are prone to learn easy solutions from superficial statistics in the data, namely shortcut learning, which impairs generalization and robustness of models. We propo…
Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models
Nicolò Botteghi, Federico Califano, Mannes Poel +1
We present a framework for safety-critical optimal control of physical systems based on denoising diffusion probabilistic models (DDPMs). The technology of control barrier function…
Embeddings between Barron spaces with higher order activation functions
Tjeerd Jan Heeringa, Len Spek, Felix Schwenninger +1
The approximation properties of infinitely wide shallow neural networks heavily depend on the choice of the activation function. To understand this influence, we study embeddings b…
Probabilistic neural networks for improved analyses with phenomenological models
C. H. Kim, K. Y. Chae, M. S. Smith +5
Physics models typically contain adjustable parameters to reproduce measured data. While some parameters correspond directly to measured features in the data, others are unobservab…
Discovering Efficient Periodic Behaviours in Mechanical Systems via Neural Approximators
Yannik Wotte, Sven Dummer, Nicolò Botteghi +3
It is well known that conservative mechanical systems exhibit local oscillatory behaviours due to their elastic and gravitational potentials, which completely characterise these pe…
Duality for Neural Networks through Reproducing Kernel Banach Spaces
Len Spek, Tjeerd Jan Heeringa, Felix Schwenninger +1
Reproducing Kernel Hilbert spaces (RKHS) have been a very successful tool in various areas of machine learning. Recently, Barron spaces have been used to prove bounds on the genera…
Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data
Nicolò Botteghi, Mengwu Guo, Christoph Brune
This work proposes a Stochastic Variational Deep Kernel Learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The fram…
Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning
Nicolò Botteghi, Luuk Grefte, Mannes Poel +4
Inspection and maintenance are two crucial aspects of industrial pipeline plants. While robotics has made tremendous progress in the mechanic design of in-pipe inspection robots, t…
Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics
Nicolò Botteghi, Mannes Poel, Beril Sirmacek +1
Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learni…
Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces
Nicolò Botteghi, Khaled Alaa, Mannes Poel +4
Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, su…
Learning normal form autoencoders for data-driven discovery of universal,parameter-dependent governing equations
Manu Kalia, Steven L. Brunton, Hil G. E. Meijer +2
Complex systems manifest a small number of instabilities and bifurcations that are canonical in nature, resulting in universal pattern forming characteristics as a function of some…
Low Dimensional State Representation Learning with Reward-shaped Priors
Nicolò Botteghi, Ruben Obbink, Daan Geijs +5
Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal polic…