946 search results for “deep learning” in the Public 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.
-
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.
-
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.
-
The use of Deep Learning in the automated detection of archaeological objects in remotely sensed data
Generally the data from remote sensing surveys - the scanning of the earth by satellite or aircraft in order to obtain information about it - is screened manually in archaeology. However, constant monitoring of the earth's surface causes a huge influx of data of high complexity and high quality. To…
-
Vietnam: Exploring the deep determinants of learning
Vietnam’s record of expanding access to education, and especially its performance on international assessments such as PISA, has raised questions about what Vietnam got right, how, and why and what insights Vietnam’s experiences might offer for efforts at improving the performance of education systems…
-
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…
-
AI-SUPPORTED SYNTHESIS OF SHEPARD-RISSET FREQUENCY SETS
Implementation of the new sound synthesis and analysis method in music composition.
-
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.
-
Julia Wasala
Science
j.wasala@liacs.leidenuniv.nl | +31 71 527 4799
-
Deep imaging
A computer can look at, and learn from, many more images than a human specialist. AI systems are rapidly becoming indispensable for medical and biological applications. But they still have to learn how to explain their decisions.
-
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.
-
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.
-
Ana Cristina Arcos Marin
Science
a.c.arcos.marin@liacs.leidenuniv.nl | +31 71 527 2727
-
Zihao Yuan
Science
z.yuan@cml.leidenuniv.nl | +31 71 527 2727
-
Daan Pelt brings theory and practice together in the field of Deep Learning
Bringing the theoretical world of mathematics and computer science to more applied research areas. That is what Daan Pelt, assistant professor at the Leiden Institute of Advanced Computer Science (LIACS) is trying to achieve with the methods he is developing as a solution to challenges in image proc…
-
Michael Lew
Science
m.s.lew@liacs.leidenuniv.nl | +31 71 527 7034
-
Aske Plaat
Science
a.plaat@liacs.leidenuniv.nl | +31 71 527 7065
-
Alan Kai Hassen
Science
a.k.hassen@liacs.leidenuniv.nl | +31 71 527 4799
-
Fons Verbeek
Science
f.j.verbeek@liacs.leidenuniv.nl | +31 71 527 5773
-
Machine Learning
Computers are capable of making incredibly accurate predictions on the basis of machine learning. In other words, these computers can learn without intervention once they have been pre-programmed by humans. At LIACS, we explore and push the borders of what a revolutionary new generation of algorithms…
-
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.
-
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.
-
Reinforcement learning
The Reinforcement Learning lab conducts research into Reinforcement Learning and Intelligent Combinatorial Algorithms.
-
A Deep History of Human Landscape Manipulation
This study aims to provide a long time perspective of human landscape manipulation. Studying the roles of prehistoric foragers in past ecosystems is of great importance to establish the character of past 'natural' landscapes and to enhance the management of current ones.
-
André Mesquita Fery Antunes
Science
a.r.mesquita.fery.antunes@liacs.leidenuniv.nl | +31 71 527 2727
-
Guilherme Perin
Science
g.perin@liacs.leidenuniv.nl | +31 71 527 2727
-
Flat but not shallow. Towards flatter representations in deep semantic parsing for precise and feasible inferencing
Simulating human language understanding on the computer is a great challenge. A way to approach it is to represent natural language meanings in logic, and to use logical provers to determine what does and does not follow from a text. What logic is best to use and how natural language meanings are best…
-
The Deep History of Human Landscape Manipulation
This project studies the roles of prehistoric foragers in past ecosystems to establish the character of past “natural” landscapes and enhance the management of current ones.
-
Natural deep eutectic solvents: A new green solvent from nature
- Which metabolites could be components of NADES? - How can we prove the presence of NADES in nature? - What are the roles of NADES in nature? - How to apply NADES in life sciences?
-
International Environmental Obligations and Liabilities in Deep Seabed Mining
On dinsdag 26 juni 2018, Linlin Sun defended her doctoral thesis ‘International Environmental Obligations and Liabilities in Deep Seabed Mining’. The doctoral research was supervised by Prof. dr. N.J. Schrijver en Prof. dr. E.C.P.D.C. De Brabandere.
-
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.
-
Deep Learning for Online Adaptive Radiotherapy
PhD defence
-
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.
-
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…
-
Lecture: Aja Huang (Google DeepMind) on AlphaGo
How did Google’s computer programme AlphaGo become so good at board game Go that it could defeat the world champion? On June 29, developer Aja Huang will speak about this during a lecture in the Gorlaeus building.
-
The deep-rooted microtonality of the bass clarinet
A new microtonal approach of the bass clarinet, to further develope the instrument’s capability to produce not only exact quartertones, but also smaller units.
-
Aja Huang: 'The power of AlphaGo is in the use of neural networks'
How did Google's computer programme AlphaGo become so powerful? On June 29, developer Aja Huang elaborated on this during a lecture in the Gorlaeus building.
-
TAILOR - Trustworthy AI through the integration of learning
The quest for Trustworthy AI is high on both the political and the research agenda, and it actually constitutes TAILOR’s first research objective (H1) of developing the foundations for Trustworthy AI. It is concerned with designing and developing AI systems that incorporate the safeguards that make…
-
2 PhD Candidates, Reinforcement Learning for Sustainable Energy
Science, Leiden Institute of Advanced Computer Science (LIACS)
-
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…
-
Deep learning for automatic segmentation of tumors on MRI
PhD defence
-
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…
-
Artificial Intelligence & Machine Learning
Computers are capable of making incredibly accurate predictions on the basis of machine learning. In other words, these computers can learn without intervention once they have been pre-programmed by humans. At LIACS, we explore and push the borders of what a revolutionary new generation of algorithms…
-
Yolinde van Paridon
Faculteit der Sociale Wetenschappen
y.van.paridon.3@fsw.leidenuniv.nl | +31 71 527 1488
-
Deep Hanging Out in the Age of the Digital; Contemporary Ways of Doing Online and Offline Ethnography
A brief review essay on some of the work that has been recently published in the emergent field of digital ethnography.