Searched for: subject%3A%22invariance%22
(1 - 20 of 101)

Pages

document
Lengyel, A. (author)
Computer vision algorithms are getting more advanced by the day and slowly approach human-like capabilities, such as detecting objects in cluttered scenes and recognizing facial expressions. Yet, computers learn to perform these tasks very differently from humans. Where humans can generalize between different lighting conditions or geometric...
doctoral thesis 2024
document
van der Kolk, Floris (author)
Machine learning on edge devices performs crucial identification or prediction tasks while limiting the amount of data that needs to be transmitted to more centralized computing nodes. However, strict area and energy requirements necessitate specialized hardware developed for the requirements of the device and model. This thesis is concerned...
master thesis 2024
document
Aubry, Augusto (author), Carotenuto, Vincenzo (author), Maio, Antonio De (author), Fioranelli, F. (author)
The design of bespoke adaptive detection schemes relying on the joint use of multistatic/polarimetric measurements requires a preliminary statistical inference on the clutter interference environment. This is of paramount importance to develop an analytic model for the received signal samples, which is mandatory for the synthesis of radar...
journal article 2024
document
Pengel, A.L. (author), Bierkens, G.N.J.C. (author)
Strong invariance principles describe the error term of a Brownian approximation to the partial sums of a stochastic process. While these strong approximation results have many applications, results for continuous-time settings have been limited. In this paper, we obtain strong invariance principles for a broad class of ergodic Markov...
journal article 2024
document
Oudejans, Benjamin (author)
In this thesis, we derive a lower bound on a quantity appearing in a Fourier multiplier inequality on solvable Lie groups.<br/>In Caspers, Janssens, Krishnaswamy-Usha and Miaskiwskyi (2022), a classical result by de Leeuw about the restriction of Fourier multipliers on $\mathbb{R}^n$ to a discrete subgroup is extended to a noncommutative setting...
master thesis 2023
document
Lieuw A Soe, Devin (author)
This paper studies the effect of integrating color equivariance and invariance into object detection, in particular into the Faster R-CNN architecture. To better understand the influence of this integration, we introduce modifications to the traditional convolutional layers of the standard Faster R-CNN model. By employing group theory in a...
master thesis 2023
document
Schermerhorn, Rick (author)
In this report we examine the dual space of $\ell^\infty$. If $p \in [1,\infty)$ and $q \in [1,\infty]$ satisfy $\frac{1}{p}+\frac{1}{q}=1$, then one can identify the spaces $\ell^q$ and $(\ell^p)'$ in a natural way via an isometric isomorphism. This identification does not extend to the case $p=\infty$ and $q=1$. We prove that the obvious...
bachelor thesis 2023
document
Manur, Suraj (author)
The integration of renewable energy systems into the grid brings new and unique propositions involving the integration of power electronic inverter based solutions into the High Voltage (HV) grid. Thus a need arises to test the HV components with unconventional waveforms which can be satisfied by the Arbitrary Waveshape Generator (AWG). Two such...
master thesis 2023
document
Beentjes, Ilse (author)
Verschillende r-expansies onderzoeken en de invariante maat numeriek benaderen, met als doel om een beeld te krijgen van de maat en verschillende waarden aan af te leiden.
bachelor thesis 2023
document
Aubry, Augusto (author), Carotenuto, Vincenzo (author), De Maio, Antonio (author), Fioranelli, F. (author)
This article deals with the statistical inference of simultaneously recorded co- and cross-polarized bistatic coherent sea-clutter returns at S-band. This study is conducted employing appropriate statistical learning tools, involving the complex envelope of data, to assess the compliance of the available measurements with the spherically...
journal article 2023
document
van Iersel, L.J.J. (author), Moulton, Vincent (author), Murakami, Yukihiro (author)
Graph invariants are a useful tool in graph theory. Not only do they encode useful information about the graphs to which they are associated, but complete invariants can be used to distinguish between non-isomorphic graphs. Polynomial invariants for graphs such as the well-known Tutte polynomial have been studied for several years, and...
journal article 2023
document
Wang, Zhen (author), Xi, Kaihua (author), Cheng, Aijie (author), Lin, H.X. (author), Ran, André C.M. (author), van Schuppen, J.H. (author), Zhang, Chenghui (author)
The synchronization of power generators is an important condition for the proper functioning of a power system, in which the fluctuations in frequency and the phase angle differences between the generators are sufficiently small when subjected to stochastic disturbances. Serious fluctuations can prompt desynchronization, which may lead to...
journal article 2023
document
Xi, Kaihua (author), Wang, Zhen (author), Cheng, Aijie (author), Lin, H.X. (author), van Schuppen, J.H. (author), Zhang, Chenghui (author)
The synchronization stability of a complex network system of coupled phase oscillators is discussed. In case the network is affected by disturbances, a stochastic linearized system of the coupled phase oscillators may be used to determine the fluctuations of phase differences in the lines between the nodes and to identify the vulnerable lines...
journal article 2023
document
Carotenuto, V. (author), Aubry, A. (author), De Maio, A. (author), Fioranelli, F. (author)
The design of bespoke adaptive detection schemes relying on the joint use of multistatic/polarimetric measurements requires a preliminary statistical inference on the clutter interference environment. This is fundamental to develop an analytic model for the received signal samples, which is used to synthesize the radar detector. In this...
conference paper 2023
document
Li, Mingwu (author), Jain, S. (author), Haller, George (author)
Dynamical systems are often subject to algebraic constraints in conjunction with their governing ordinary differential equations. In particular, multibody systems are commonly subject to configuration constraints that define kinematic compatibility between the motion of different bodies. A full-scale numerical simulation of such constrained...
journal article 2023
document
Kekkonen, H.N. (author), Lassas, Matti (author), Saksman, Eero (author), Siltanen, Samuli (author)
We propose alternatives to Bayesian prior distributions that are frequently used in the study of inverse problems. Our aim is to construct priors that have similar good edge-preserving properties as total variation or Mumford-Shah priors but correspond to well-defined infinite-dimensional random variables, and can be approximated by finite...
journal article 2023
document
Zhu, Yujin (author)
Tabular data synthesis is a promising approach to circumvent strict regulations on data privacy. Although the state-of-the-art tabular data synthesizers, e.g., table-GAN, CTGAN, TVAE, and CTAB-GAN, are effective at generating synthetic tabular data, they are sensitive to column permutations of input data. In this work, we conduct an impact and...
master thesis 2022
document
Cardiff Aleu, Joana (author)
The design of wind turbines is an iterative process in which load calculations and system performance analyses are done under various environmental conditions. Due to the complexity of wind turbine systems, fully coupled aero-hydro-servo-elastic codes are indispensable to represent the nonlinear behaviour of the system. However, nonlinear codes...
master thesis 2022
document
Tjiam, Yuan (author)
Surgical teams use instrument counts to prevent leaving unintended objects in patients. This is done manually, but could potentially be done through computer vision software. This paper presents a proof of concept for detecting instruments in the operating room with the Scale Invariant Feature Transform (SIFT). The SIFT algorithm is explored and...
master thesis 2022
document
van Lith, Jochem (author)
Learning algorithms can perform poorly in unseen environments when they learn<br/>spurious correlations. This is known as the out-of-domain (OOD) generalization problem. Invariant Risk Minimization (IRM) is a method that attempts to solve this problem by learning invariant relationships. Motivating examples as well as counterexamples have been...
bachelor thesis 2022
Searched for: subject%3A%22invariance%22
(1 - 20 of 101)

Pages