Neuro-GOMEA: Using Modern Evolutionary Algorithms to Train Neural Networks

Neural networks (NNs) have, in recent years, become a major part of modern pattern recognition, and both theoretical and applied research evolve at an astounding pace. NNs are usually trained via gradient descent (GD), but research has shown that GD is not always capable of training very small networks. As a result, networks trained via GD are...

Safety Performance Boundary Identification of Highly Automated Vehicles: A Surrogate Model-Based Gradient Descent Searching Approach

Highly automated vehicles (HAVs) have been introduced to the transportation system for the purpose of providing safer mobility. Considering the expected long co-existence period of HAVs and human-driven vehicles (HDVs), the safety operation of HAVs interacting with HDVs needs to be verified. To achieve this, HAVs' Operational Design Domain ...

Efficient Bayesian Uncertainty Estimation for nnU-Net

The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible...

First-order methods to recover the measurement operators and states of bipartite quantum correlations

In this thesis, we start with giving a mathematical description of bipartite quantum correlations and how they are built up in the Tensor model. This is needed because we want to recover the state and the operators when only the bipartite quantum correlation is known. In the literature, there are see-saw algorithms to...

David and the vegetable factory: A Two-stage Optimization Model for Generating a Vegetable Factory's Facility Layout Using the Gradient Descent Approach

In this thesis a two-stage model is proposed, combining the idea of a two-stage model from Anjos and Vieira [1] with a gradient descent approach, much like proposed in Sikaroudi and Shahanaghi [42], in order to solve the facility layout problem for problems consisting of 8 and 12 departments . This method was chosen after analyzing the criteria...

Predictive Modelling of Asphalt Concrete Functional Properties Using Multiple Linear Regression and Gradient Boosting

Despite therelevance of the road infrastructure, the mechanisms governing the mechanicalproperties of asphalt concrete pavements, are currently not sufficientlyunderstood. Many empirical models of different complexity are proposed in theliterature; however, (i) they all have below high (R2 =0.85) predictiveaccuracy; (ii)...

Measurement Light Bulb: Control

This document describes the design process the prototype of a measurement light bulb which is able to project spherical harmonics of orders 0-1-2. Photographs of these projections can be combined to represent many light distributions. The measurement light bulb can be used in the field of research focused on the computation of the illumination...

In-flight model parameter and state estimation using gradient descent for high-speed flight

High-speed flight in GPS-denied environments is currently an important frontier in the research on autonomous flight of micro air vehicles. Autonomous drone races stimulate the advances in this area by representing a very challenging case with tight turns, texture-less floors, and dynamic spectators around the track. These properties hamper...

Comparison of bounds for optimal PMU placement for state estimation in distribution grids

The lack of measurements in distribution grids poses a severe challenge for their monitoring: Since there may not be enough sensors to achieve numerical observability, so load forecasts (pseudo-measurements) are typically used, and thus an accurate state estimation is not guaranteed. However, estimation is required to control distribution...

Modelling epidemic spreading phenomena processes on networks

Spreading processes are ubiquitous in nature and societies, e.g. spreading of diseases and computer virus, propagation of messages, and activation of neurons. Computer viruses cause an enormous economic loss. Moreover, many illnesses/diseases still causing a serious threat to public health. For example, the outbreaks of circulating influenza...

Membrane mediated interactions and pattern formation of conical inclusions on a flat membrane

In this thesis, we investigate interactions between conical inclusions in a lipid bilayer membrane and make predictions about the patterns they form. To find these patterns, we derive an expression for the energy of a membrane as a function of the inclusion locations and search numerically for the pattern<br/>that gives minimum energy.<br/><br/...

Design of an Aberration Correction System for a Deployable Space Telescope

Launch costs for high-resolution space telescopes for Earth observation can be reduced when the telescope mirrors are made deployable. However, such a system is subject to optical aberrations that decreases image quality. To counter these aberrations, an Aberration Correction System (ACS) is proposed that uses a deformable mirror (DM) which is...

GPU-based stochastic-gradient optimization for non-rigid medical image registration in time-critical applications

Currently, non-rigid image registration algorithms are too computationally intensive to use in time-critical applications. Existing implementations that focus on speed typically address this by either parallelization on GPU-hardware, or by introducing methodically novel techniques into CPU-oriented algorithms. Stochastic gradient descent (SGD...

Stochastic optimization with randomized smoothing for image registration

Image registration is typically formulated as an optimization process, which aims to find the optimal transformation parameters of a given transformation model by minimizing a cost function. Local minima may exist in the optimization landscape, which could hamper the optimization process. To eliminate local minima, smoothing the cost function...

An Online Learning Approach to Eliminate Bus Bunching in Real-time

Recent advances in telecommunications created new opportunities for monitoring public transport operations in real-time. This paper presents an automatic control framework to mitigate the Bus Bunching phenomenon in real-time. The framework depicts a powerful combination of distinct Machine Learning principles and methods to extract valuable...

Anomaly detection for internet banking using supervised learning on high dimensional data

Nowadays, a high number of transactions are performed via internet banking. Rabobank processes more than 10 million transactions per day. Most of these transactions are (part of) normal behaviour. On the other hand, some transactions are considered to be out of the ordinary. These anomalous events occur relatively infrequently (less than 10 per...

Close formation flight control - with applications in commercial aviation

Ever since the beginning of manned flight, engineers have been inspired by nature in many ways. Birds have been flying in formation for as long as man remember and military aircraft followed suit. In the light of rising fuel prices, crowded airspace and stringent environmental regulations, formation flight could just be another leap forward in...