document

The Relation Between Words and Definitions in Combined Word-Sentence Space

Verschuuren, Rolf (author)

Methods for learning vector space representations of words have yielded spaces which contain semantic and syntactic regularities. These regularities mean that vector arithmetic operations in the latent space represent meaningful and interpretable relations between words. These word vectors have been so successful in capturing such relations, as...

master thesis 2021

document

Regularization Effect of Dropout

Zhao, Xunyi (author)

Dropout is one of the most popular regularization methods used in deep learning. The general form of dropout is to add random noise to the training process, limiting the complexity of the models and preventing overfitting. Evidence has shown that dropout can effectively reduce overfitting. This thesis project will show some results where dropout...

master thesis 2021

document

Energy accounting of the black box: An exploratory study of the restrictions on accounting the energy consumption of training deep learning models in data centers

Kloosterman, Frank (author)

master thesis 2021

document

UNet-based Fully-automatic Segmentation of the Capitate from CT Images

Xue, Wenli (author)

Osteoarthritis (OA) is a degenerative joint disease and imposes an increasing burden on individuals and public health systems. Most prevalent joints are the knee, hip and hands, including the wrist. In order to enable early treatment of wrist OA, an early-detection method of cartilage loss, a characteristic symptom of OA, is needed. , CT images...

master thesis 2021

document

Sample-efficient multi-agent reinforcement learning using learned world models

Willemsen, Daniël (author)

Multi-agent robotic systems could benefit from reinforcement learning algorithms that are able to learn behaviours in a small number trials, a property known as sample efficiency. This research investigates the use of learned world models to create more sample-efficient algorithms. We present a novel multi-agent model-based reinforcement...

master thesis 2021

document

On the Sequential Data Models in Side-Channel Analysis: RNN, LSTM, GRU Hyperparameters, Autoencoder and Embedding Layer

Mulders, Maurits (author)

A side-channel attack is performed by analyzing unwanted physical leakage to achieve a more effective attack on the cryptographic key. An attacker performs a profiled attack when he has a physical and identical copy of the target device, meaning the attacker is in full control of the target device. Therefore, these profiled attacks are known as...

master thesis 2020

document

Predicting pedestrian path using optical flow as context cue

Tomy, Abhishek (author)

A human driver can gauge the intention and signals given by other road users indicative of their future behaviour. The intentions and signals are identified by looking at the cues originating from vulnerable road users or their surroundings (hand signals, head orientation, posture, traffic signals, distance to curb, etc.). Taking all these cues...

master thesis 2020

document

Learning Interaction-Aware Trajectory Predictions for Multi-Robot Motion Planning

Martinez Claramunt, F. (author)

Multi-robot motion planning without a central coordinator usually relies on the sharing of planned trajectories among the robots via wireless communication in order to achieve predictive collision avoidance. Path planners found in the literature that feature this scheme usually boast levels of performance comparable with their centralized...

master thesis 2020

document

A Novel Method for Solving High-Dimensional Backward Stochastic Differential Equations Using Malliavin Calculus and Deep Learning

Négyesi, Bálint (author)

Backward stochastic differential equations (BSDE) are known to be a powerful tool in mathematical modeling due to their inherent connection with second-order parabolic partial differential equations (PDE) established by the non-linear Feynman-Kac relations. The fundamental power of BSDEs lies in the fact that with them one does not merely obtain...

master thesis 2020

document

Design of a Graph Neural Network: to predict the optimal resolution of the Sonar Performance Model

Pietrak, Jakub (author)

Graph Neural Networks are a unique type of Deep Learning models that have a capability to exploit an explicitly stated structure of data representation. By design they carry a strong relational inductive bias, which is a set of assumptions that makes the algorithm prioritize some solutions over another, independent of observed data. This makes...

master thesis 2020

document

Weight Swapping: A new method for Supervised Domain Adaptation in Computer Vision using Discrete Optimization

Datta, Leonid (author)

Training Convolutional Neural Network (CNN) models is difficult when there is a lack of labeled training data and no unlabeled data is available. A popular method for this is domain adaptation where the weights of a pre-trained CNN model are transferred to the problem setup. The model is pre-trained on the same task but in a different domain...

master thesis 2020

document

Investigating Physics-Informed Neural Networks for solving PDEs

Wasei, E.A.A. (author)

Physics-Informed Neural Networks (PINNs) are a new class of numerical methods for solving partial differential equations (PDEs) that have been very promising. In this paper, four different implementations will be tested and compared. These include: the original PINN functional with equal weights for the interior and boundary loss, the same...

bachelor thesis 2020

document

Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification task

Cian, David (author)

In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them. We evaluate them on two criteria, the improvement of the network's core performance and the trust they are able to generate for users of the system. We nd that in...

bachelor thesis 2020

document

Applying Machine Learning to Learn System Dynamics Models for Urban Systems

Yin, Rukai (author)

System Dynamics (SD) is an approach to study the nonlinear behaviour of complex systems over time. SD models provide a high­level understanding of the system and aid in designing policies to achieve specific system behaviours. Conventional SD modelling requires an intensive amount of time, human resources and effort. Applying Machine Learning ...

master thesis 2020

document

Predicting high order Reduced Order Model coefficients for proton therapy dose approximations using deep learning

Bougrimov, Denis (author)

The advantage of using protons to irradiate a tumour in cancer treatment, is that the energy can be delivered very precisely to the tumour without irradiating much of the surrounding tissue. The disadvantage of this is that small displacements of a patient can result in large deviations in the planned dose delivery according to the treatment...

bachelor thesis 2020

document

Road Detection from Remote Sensing Imagery

Kaniouras, Pantelis (author)

Road network maps facilitate a great number of applications in our everyday life. However, their automatic creation is a difficult task, and so far, published methodologies cannot provide reliable solutions. The common and most recent approach is to design a road detection algorithm from remote sensing imagery based on a Convolutional Neural...

master thesis 2020

document

Analysis of the effect of caching convolutional network layers on resource constraint devices

van Lil, Wouter (author)

Using transfer learning, convolutional neural networks for different purposes can have similar layers which can be reused by caching them, reducing their load time. Four ways of loading and executing these layers, bulk, linear, DeepEye and partial loading, were analysed under different memory constraints and different amounts of similar networks...

bachelor thesis 2020

document

A Literature Study into Hyperparameter Systematization for Deep Learning-based Side-Channel Analysis

Mulder, Doreen (author)

With the recent increase in computational power, deep learning is being applied in many different fields. Deep learning has produced promising results in the field of side-channel analysis. However, the algorithms used to construct deep neural networks remain black boxes, which makes it hard to fully employ the capabilities of attacks performed...

bachelor thesis 2020

document

Application of Deep Learning to Coherent Fourier Scatterometry data

Davidse, Davy (author)

This thesis discusses the application of deep learning to Coherent Fourier<br/>Scatterometry data in order to quickly and reliably detect nanoparticles on<br/>surfaces. An introduction to deep learning is followed by a review of the<br/>experimental setup and used software. After that, results are presented of<br/>classification accuracy tests...

master thesis 2020

document

Breakpoint detection through neural nets: A feasibility study

Dijkstra, Fokke (author)

A variety of statistical methods are available to detect sudden changes, or breakpoints, in time series when used as multi-temporal change detection technique. However, these methods are unreliable in the presence of noise. Neural nets might detect breakpoints better. These deep learning models are able to generalize and optimize well, even in...

master thesis 2020