572 zoekresultaten voor “neural networks” in de Publieke website
-
stability of delay differential equations with applications to neural networks
Promotor: S.M. Verduyn Lunel, Co-Promotor: O.W. van Gaans
-
Efficient Brain Computer Interface Character Speller: Convolutional Neural Network based Methods
A P300-based Brain Computer Interface character speller, also known as P300 speller, has been an important communication pathway, under extensive research, for people who lose motor ability, such as patients with Amyotrophic Lateral Sclerosis or spinal-cord injury because a P300 speller allows human-beings…
-
System-level design for efficient execution of CNNs at the edge
A convolutional neural network (CNN) is a biologically inspired algorithm, highly capable at processing images and videos.
-
Exploring Deep Learning for Intelligent Image Retrieval
This thesis mainly focuses on cross-modal retrieval and single-modal image retrieval via deep learning methods, i.e. by using deep convolutional neural networks.
-
Deep learning for tomographic reconstruction with limited data
Tomography is a powerful technique to non-destructively determine the interior structure of an object.Usually, a series of projection images (e.g.\ X-ray images) is acquired from a range of different positions.
-
Multi-dimensional feature and data mining
In this thesis we explore machine and deep learning approaches that address keychallenges in high dimensional problem areas and also in improving accuracy in wellknown problems. In high dimensional contexts, we have focused on computational fluid dynamics (CFD) simulations.
-
Understanding deep meta-learning
The invention of neural networks marks a critical milestone in the pursuit of true artificial intelligence. Despite their impressive performance on various tasks, these networks face limitations in learning efficiently as they are often trained from scratch.
-
Machine learning and computer vision for urban drainage inspections
Sewer pipes are an essential infrastructure in modern society and their proper operation is important for public health. To keep sewer pipes operational as much as possible, periodical inspections for defects are performed.
-
Annelot Bosman
Wiskunde en Natuurwetenschappen
a.w.bosman@liacs.leidenuniv.nl | +31 71 527 4799
-
Functional fluorescent materials and migration dynamics of neural progenitor cells
In this thesis, time-lapse fluorescent microscopy plays a pivotal role in investigating functional materials within living cells as well as the migratory behaviour of neural progenitor cells.
-
Breaking of ensemble equivalence for complex networks
For many system in statistical physics the microcanonical and canonical ensemble are equivalent in the thermodynamic limit, but not for all.
-
NETWORKS
Den Hollander
-
Long term dynamics of stochastic evolution equations
Promotor: S.M. Verduyn Lunel, Co-promotor: O. van Gaans
-
Transnational networks and domestic agencies
Doordat markten in toenemende mate zijn geïnternationaliseerd, zijn (sub-)nationale toezichthouders ook steeds vaker internationaal actief. Binnen vormen van internationale netwerksamenwerking wisselen deze toezichthouders onderling informatie uit en onderhandelen ze over internationale standaarden…
-
Large scale visual search
Promotor: J.N. Kok, Co-promotor: M.S. Lew
-
Constrained and Multirate Training of Neural Networks
Lezing
-
Exploration on and of Networks
This dissertation consists of two parts, with the common theme
-
LGBT+ Network
Het LGBT+ Network biedt een platform aan alle lesbische, homoseksuele, biseksuele, transgender, intersekse en queer medewerkers en studenten van de Universiteit Leiden.
-
On metrics and models for multiplex networks
In this thesis, we extend the concept of null models as canonical ensembles of multi-graphs with given constraints and present new metrics able to characterize real-world layered systems based on their correlation patterns.
-
Network flow algorithms for discrete tomography
Promotor: R. Tijdeman, Co-promotor: H.J.J. te Riele
-
Accurate modeling of the dynamics of dissociative chemisorption on metal surfaces
Fundamental understanding of molecular reactions on metal surfaces is important for improving heterogeneous catalysis.
-
Many objective optimization and complex network analysis
This thesis seeks to combine two different research topics; Multi-Objective Optimization and Complex Network Analysis.
-
Bayes and Networks
Promotor: A.W. van der Vaart
- Quantum Networks and Sensing
-
Complex networks in perspective
Congres/symposium
-
Network analysis methods for smart inspection in the transport domain
Transport inspectorates are looking for novel methods to identify dangerous behavior, ultimately to reduce risks associated to the movements of people and goods. We explore a data-driven approach to arrive at smart inspections of vehicles.
-
Data-Driven Risk Assessment in Infrastructure Networks
Leiden University and the Ministry of Infrastructure and Water Management are involved in a collaboration in the form of a research project titled 'Data-Driven Risk Assessment in Infrastructure Networks'
-
information and variational Bayes in high dimensional statistical network inference
This thesis develops statistical methods for the analysis of high dimensional data: high dimensional networks reconstruction (Chapters 1-4), incorporation of prior information in networks reconstruction (Chapters 2-4), incorporation of prior knowledge in genetic association studies (Chapter 3).
-
AI & Art: Aesthetics and Politics of Artificial Neural Networks
Kunst en cultuur, Artist Lecture & Workshop
-
How Jihadist Networks Operate
De recente terroristische aanslagen in Europa zijn vermoedelijk niet alleen acties van individuen, maar acties gefaciliteerd door grotere jihadistische netwerken. Maar hoe opereren dit soort netwerken? Door inzicht te krijgen in hun modus operandi kunnen terroristische dreigingen worden voorkomen.
-
Numerical exploration of statistical physics
In this thesis, we examine various systems through the lens of several numerical methods.
-
Real-time foresight: preparedness for dynamic innovation networks
Promotor: H.J. van den Herik, B.R. Katzy, Co-promotor: K. Sailer
-
Resource allocation in networks via coalitional games
Promotor: F. Arbab, R. De Nicola, Co-Promotor: M. Tribastone
-
Design and application of dextran based cross-linked networks
This thesis describes the design, characterization and application of dextran based crosslinked network.
-
Estimation and Optimization of the Performance of Polyhedral Process Networks
Promotor: Prof.dr.ir. E. Deprettere
-
Computational optimisation of optical projection tomography for 3D image analysis
Optical projection tomography (OPT) is a tomographic 3D imaging technique used for specimens in the millimetre scale.
-
Searching by Learning: Exploring Artificial General Intelligence on Small Board Games by Deep Reinforcement Learning
In deep reinforcement learning, searching and learning techniques are two important components. They can be used independently and in combination to deal with different problems in AI, and have achieved impressive results in game playing and robotics. These results have inspired research into artificial…
-
Wireless Random-Access Networks and Spectra of Random Graph
This thesis is divided into two parts. In Part I we study metastability properties of queue-based random-access protocols for wireless networks. The network is modeledas a bipartite graph whose edges represent interference constraints. In Part II we study spectra of inhomogeneous Erdős-Rényi random…
-
Population-Scale Network Analysis (POPNET)
Een infrastructuur voor onderzoeksdata in computationele sociale wetenschappen
-
PUPOL Netwerk: Academic Network Public and Political Leadership
Onderzoekers aangesloten bij het Leiden Leadership Centre zijn actieve leden van het PUPOL netwerk. PUPOL is een internationaal academisch netwerk voor publiek en politiek leiderschap. Dit netwerk stimuleert de uitwisseling van ideeën en bevordert gezamenlijk onderzoek tussen wetenschappers gericht…
-
Solution for Critical Raw Materials - an European Export Network (SCRREEN)
Where and how are critical materials currently used and how can this information be used to develop scenarios about their future demand.
-
Leukemia treatment & cognitive development
-
-
Machine learning for radio galaxy morphology analysis
We explored how to morphologically classify well-resolved jetted radio-loud active galactic nuclei (RLAGN) in the LOw Frequency Array (LOFAR) Two-metre Sky Survey (LoTSS) using machine learning.
-
Clavis Aurea? Structure-enabled approaches of identifying and optimizing GPCR ligands
Promotores: A.P. IJzerman, H.W.T. van Vlijmen
-
Chainet - European network on chain analysis for environmental decision support
Analytical tools for environmental design and management in a systems perspective. The combined use of analytical tools.
-
Semi-partitioned Scheduling and Task Migration in Dataflow Networks
Promotor: Ed F. Deprettere, Co-promotor: Todor P. Stefanov
-
Developmental effects of polystyrene nanoparticles in the chicken embryo
There is concern about the threat that nanoplastics (NPs) may pose to both wildlife and humans. This thesis explores the mechanisms of toxicity of polystyrene nanoparticles (PS-NPs) in chicken embryo.
-
Visual Relation extraction Based on Deep Cross-media Transfer Network
Building a Deep Cross-media Transfer Network to extract visual relations that relieve the problem of insufficient training data for visual tasks.
-
Development of an in vitro vascular network using zebrafish embryonic cells
One of the major limitations in culturing complex tissues or organs is the lack of vascularization in the cultured tissue. Development of a functional capillary bed could overcome this problem.
-
Moved by the tears of others: emotion networking in the heritage sphere
There is no heritage without emotional sharing and clashing. This article explores the involvement of divergent emotions in heritage making by discussing the debate series of Imagine IC and the Reinwardt Academy and zooming in on the commemoration of slavery and imagery of ‘Black Pete’ in the Netherlands.…