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.

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.

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.

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.

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.

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.

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…

Implementation of the new sound synthesis and analysis method in music composition.

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.

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.

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.

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.

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…

Thanks to deep learning, computer program AlphaZero plays better chess than the best person. The computer wins because it can predict further ahead than a human being through pattern recognition. Aske Plaat discusses this special development in Dutch newspaper NRC. He expects the major tech companies…

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.

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.

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…

Supercomputer ALICE has been expanded, making it even more powerful and faster. This means researchers and students can work with heavier models. From language research to brain activity scans, this expansion is good news for a variety of disciplines. So who gets to work with this prima donna?

Developing new drugs is a difficult process. With the aid of artificial intelligence, Pharmaceutical scientist Xuhan Liu has developed methods that can help make drug design cheaper and faster. PhD defence on 15 February.

Wouter Verschoof-van der Vaart has developed a way to use Deep Learning and geography software to rapidly and systematically map prehistoric barrows, Celtic fields, and medieval charcoal kilns. This innovative method has been tested on high-resolution elevation maps from the Veluwe, the Netherlands.…

In the BNR Newsradioprogram De Nieuwe Wereld, professors Aske Plaat (Data Science) and Catholijn Jonker (Explainable AI) of the computer science institute of Leiden University discuss about decisions made by computers. From self-driving cars to intelligent soap pumps: should we be able to follow the…

Optical projection tomography (OPT) is a tomographic 3D imaging technique used for specimens in the millimetre scale.

The coronavirus has the world in its grip. Finding a cure has never been more important. Unfortunately, the development of new drugs for treatment of the COVID-19 disease caused by the virus and development of a vaccine are complex, lengthy, and above all costly processes. With the help of computer…