1,448 zoekresultaten voor “deep learning” in de Publieke website
-
Deep learning for visual understanding
With the dramatic growth of the image data on the web, there is an increasing demand of the algorithms capable of understanding the visual information automatically.
-
Exploring deep learning for multimodal understanding
This thesis mainly focuses on multimodal understanding and Visual Question Answering (VQA) via deep learning methods. For technical contributions, this thesis first focuses on improving multimodal fusion schemes via multi-stage vision-language interactions.
-
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.
-
Risk bounds for deep learning
In this thesis, deep learning is studied from a statistical perspective. Convergence rates for the worst case risk bounds of neural network estimators are obtained in the classification, density estimation and linear regression model.
-
Exploring Images With Deep Learning for Classification, Retrieval and Synthesis
In 2018, the number of mobile phone users will reach about 4.9 billion. Assuming an average of 5 photos taken per day using the built-in cameras would result in about 9 trillion photos annually.
-
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.
-
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.
-
Exploring Open-World Visual Understanding with Deep Learning
We are living in an information era where the amount of image and video data increases exponentially.
-
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…
-
Information Diffusion Analysis in Online Social Networks based on Deep Representation Learning
With the emergence of online social networks (OSNs), the way people create and share information has changed, which becomes faster and broader than traditional social media.
-
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.
-
Machine Learning
Computers zijn in staat om ongelooflijk nauwkeurige voorspellingen te doen op basis van machine learning. Met andere woorden, deze computers kunnen zonder tussenkomst leren als ze eenmaal door mensen zijn voorgeprogrammeerd. Bij LIACS verkennen en verleggen we de grenzen van wat een revolutionaire nieuwe…
-
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.
-
Daan Pelt brengt de theorie en praktijk van Deep Learning dichterbij elkaar
De theoretische wereld van wiskunde en informatica naar meer toegepaste onderzoeksgebieden brengen. Dat is wat Daan Pelt, universitair docent bij het Leiden Institute of Advanced Computer Science (LIACS) probeert te bereiken met de methodes die hij ontwikkelt als oplossing voor uitdagingen in beeldv…
-
Spectral imaging and tomographic reconstruction methods for industrial applications
Radiography is an important technique to inspect objects, with applications in airports and hospitals. X-ray imaging is also essential in industry, for instance in food safety checks for the presence of foreign objects.
-
2 PhD Candidates, Reinforcement Learning for Sustainable Energy
Wiskunde en Natuurwetenschappen, Leiden Institute of Advanced Computer Science (LIACS)
-
Aspects of the analysis of cell imagery: from shape to understanding
In this thesis, we have studied cell images from two types of cells, including pollen grains and the immune cells, neutrophils. These images are captured using a bright field microscope and a confocal microscope.
-
To explore the drug space smarter: Artificial intelligence in drug design for G protein-coupled receptors
Over several decades, a variety of computational methods for drug discovery have been proposed and applied in practice. With the accumulation of data and the development of machine learning methods, computational drug design methods have gradually shifted to a new paradigm, i.e. deep learning methods…
-
Computational speedups and learning separations in quantum machine learning
This thesis investigates the contribution of quantum computers to machine learning, a field called Quantum Machine Learning. Quantum Machine Learning promises innovative perspectives and methods for solving complex problems in machine learning, leveraging the unique capabilities of quantum computers…
-
Risk bounds for deep learning
Promotie
-
Luc SträterWiskunde en Natuurwetenschappen
l.p.j.strater@liacs.leidenuniv.nl | +31 71 527 2727
-
André Mesquita Fery AntunesWiskunde en Natuurwetenschappen
a.r.mesquita.fery.antunes@liacs.leidenuniv.nl | +31 71 527 2727
-
Massively collaborative machine learning
Promotor: J. N. Kok, Co-promotor: A. J. Knobbe
-
Learning-based Representations of High-dimensional CAE Models for Automotive Design Optimization
In design optimization problems, engineers typically handcraft design representations based on personal expertise, which leaves a fingerprint of the user experience in the optimization data. Thus, learning this notion of experience as transferrable design features has potential to improve the performance…
-
Kunstmatige intelligentie en machine learning
Computers zijn in staat om ongelooflijk nauwkeurige voorspellingen te doen op basis van machine learning. Met andere woorden, deze computers kunnen zonder tussenkomst leren als ze eenmaal door mensen zijn voorgeprogrammeerd. Bij LIACS verkennen en verleggen we de grenzen van wat een revolutionaire nieuwe…
-
Julia WasalaWiskunde en Natuurwetenschappen
j.wasala@liacs.leidenuniv.nl | +31 71 527 4799
-
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.
-
Suzan Verberne in de Volkskrant over nieuwe vertaaltechnologieën
Een intelligente vertaalmachine gebaseerd op nieuwe ontwikkelingen in machine learning gaat de concurrentie aan met grote vertaalservices als die van Google. Maar ook Google maakt grote vorderingen sinds het is het is overgestapt op deep learning, aldus informatica-onderzoeker Suzan Verberne in de V…
-
Deep Learning for Online Adaptive Radiotherapy
Promotie
-
Exploring Deep Learning for Multimodal Understanding
Promotie
-
PhD in Machine Learning for Quantum Systems
Wiskunde en Natuurwetenschappen, Leiden Institute of Advanced Computer Science (LIACS)
-
Applications of Natural Deep Eutectic Solvents to Extraction and Preservation of Biomolecules
The recently introduced nature-originated deep eutectic solvents, so-called natural deep eutectic solvents (NADES) are considered as truly green solvents, which composed of natural ingredients found abundantly in organisms.
-
International Environmental Obligations and Liabilities in Deep Seabed Mining
Op dinsdag 26 juni 2018 verdedigde Linlin Sun haar proefschrift ‘International Environmental Obligations and Liabilities in Deep Seabed Mining’. Het onderzoek is begeleid door promotoren prof. dr. N.J. Schrijver en prof. dr. E.C.P.D.C. De Brabandere.
-
Aske Plaat in NRC over het succes van computerprogramma AlphaZero
Dankzij deep learning schaakt computerprogramma AlphaZero beter dan de beste mens. De computer wint omdat hij door patroonherkenning verder vooruit kan rekenen dan een mens. In NRC bespreekt Aske Plaat deze bijzondere ontwikkeling. Hij verwacht dat de grote techbedrijven er alles aan zullen doen om…
-
Professional learning: what teachers want to learn
Het doel van dit promotieonderzoek was te onderzoeken wat leraren zelf willen leren. De centrale onderzoeksvraag luidde: wat, hoe en waarom willen leraren leren? En hangt dit af van hun jaren leservaring en de school waarin ze werken?
-
On the optimization of imaging pipelines
In this thesis, topics relating to the optimization of high-throughput pipelines used for imaging are discussed. In particular, different levels of implementation, i.e., conceptual, software, and hardware, are discussed and the thesis outlines how advances on each level need to be made to make gains…
-
Lezing: Aja Huang (Google DeepMind) over AlphaGo
Hoe is Google’s computerprogramma AlphaGo zo goed geworden in bordspel Go dat het de wereldkampioen kon verslaan? Op 29 juni vertelt ontwikkelaar Aja Huang daarover tijdens een lezing in het Gorlaeusgebouw.
-
Betrokkenheid van studenten bij blended learning in het hoger onderwijs
Op welke manier kunnen docenten de betrokkenheid van studenten ondersteunen en vergroten in de context van blended learning?
-
Learning from small samples
Learning from small data sets in machine learning is a crucial challenge, especially when dealing with data imbalances and anomaly detection. This thesis delves into the challenges and methodologies of learning from small datasets in machine learning, with a particular focus on addressing data imbalances…
-
Jaap van den Herik vertelt in de Volkskrant en op BNR over AlphaGo en Diplomacy
De voorspelling van Jaap van den Herik, directeur van het Leiden Centre of Data Science, is uitgekomen: Google-computer AlpaGo heeft de wereldkampioen Go verslagen met 4-1. In interviews met de Volkskrant en BNR Nieuwsradio vertelt Van den Herik over het toernooi én over de volgende uitdaging: het spel…
-
Deep learning for tomographic reconstruction with limited data
Promotie
-
Learning My Way
Learning about My meaningful Way through life and profession.
-
Exploring Open-World Visual Understanding with Deep Learning
Promotie
-
E-learning ECMO
Deze e-learning vergroot uw theoretische kennis met betrekking tot de bediening van het Extra Corporele Membraan Oxygenatie (ECMO) systeem, de verschillende ECMO typen met indicaties en contra-indicaties en de meest voorkomende complicaties.
-
Diepzinnige beeldvorming
Een computer kan veel meer beelden bekijken, en er van leren, dan een menselijke specialist. Voor medische en biologische toepassingen worden AI-systemen in hoog tempo onmisbaar. Ze moeten nog wel leren uitleggen hoe ze tot hun oordeel komen.
-
Deep learning for automatic segmentation of tumors on MRI
Promotie
-
Aja Huang: ‘De kracht van AlphaGo zit in het gebruik van neurale netwerken’
Hoe is Google’s computerprogramma AlphaGo zo krachtig geworden? Op 29 juni vertelde ontwikkelaar Aja Huang daarover tijdens een lezing in het Gorlaeusgebouw.
-
Centre for Professional Learning
Opleidingen voor professionals op academisch niveau om vraagstukken van vandaag en morgen rondom beleid en bestuur op te lossen. Het team van CPL bestaat uit academische professionals in public affairs, veiligheid, diversiteit en inclusie, publiek leiderschap, legal technology en communicatie.
-
Bayesian learning: challenges, limitations and pragmatics
This dissertation is about Bayesian learning from data. How can humans and computers learn from data?
-
Nonverbal Learning Disorder (NLD)
-