|
I want to understand how neural systems perform visual perception. At the interface of computer vision and neuroscience, I try to understand both how biological vision works and how to teach computers to make sense of images. I use an interdisciplinary approach that combines methods from machine learning and computer vision with behavioral studies and neuronal population recordings in the brain.
+49 551 39 21272
Room: 2.137
Email
|
|
+49 551 39 21160
Room: 2.140
Email
|
|
My research focuses on applying scalable machine learning methods to perceive, understand and represent dynamic scenes. Particularly, I am interested in techniques for sample-efficient and unsupervised learning. My long-term goal is to enable systems to act autonomously - so I can watch them while they do my work.
Room: 2.132
Email
|
|
My research goal is to understand how visual perception in the brain works and how to apply this knowledge to improve perception in artificial neural networks. I work at the intersection of computational neuroscience and machine learning. I’m especially interested in unsupervised representation learning and to understand how the notion of objects arises in visual perception in biological systems and how we can use this knowledge to improve scene understanding of artificial neural networks.
Room: 2.127
Email
|
|
Coming from graph learning and learning theory, I am interested in ways to use machine learning techniques to solve actual scientific questions in physics and biology. Furthermore, I like to think about ways in which we can use deep learning to solve or approximate NP hard problems such as graph coloring.
Room: 1.116
Email
|
|
My research is focused on developing models that can learn the interactions and dynamics of moving objects from videos. For this purpose, I have been working on attention-based (self) supervised, semi-supervised and object-centric learning methods. Such object-interaction learned models hold potential for applications in areas such as multi-object tracking, segmentation of moving objects, and video instance segmentation. In addition to my primary research interests, I am also involved in projects related to active learning, and action and interaction recognition.
Email
|
|
Coming from theoretical physics, I like to look for symmetries and invariant quantities in systems. If the problem at hand, the system to understand, has too many degrees of freedom, finding such symmetries and invariant quantities can help simplify the problem and give us a better understanding of it. While training deep learning models, I like to look for symmetries and invariant quantities in the dataset, try to have a representation of it on some manifold, and consider corresponding geometry while selecting a neural network to attack the problem. Currently, I am working on the inverse problem of holography reconstruction. The aim is to reconstruct the position, size and shape of cloud particles.
Room: 2.125
Email
|
|
I work with computer vision techniques to help researchers who study social relationships of monkeys in the wild. Watching hours of video material can be tiring and a source for mistakes. I want to automate and improve this process by training deep learning algorithms to understand and analyze what is happening in the videos.
Room: 1.115
Email
|
|
Curiosity is a major driver for living creatures to learn or invent. The aim of my work is to tackle the understanding and predictability of this characteristic, utilizing eye tracking data from humans combined with neural networks to explore different aspects of this topic. Additionally, my focus is on studying how this behavior can enhance learning efficiency in deep learning methods.
Room: 1.111
Email
|
|
I am interested to understand how brain activity develops with time and how previous sensory input influences the processing of the current stimulus. I work with calcium data from a mouse brain. Also, I believe that deep learning should not only produce good scores but also be interpretable and have biological meaning. I hope to find such interpretable models during my Ph.D.
Room: 2.127
Email
|
|
The visual system does not act as a mere camera. As early as in the retina, the brain starts to interpret the information it receives in order to build the perception of visual reality we experience. My goal is to shed more light on this process. Taking advantage of recent deep learning methods, I work on building retinal models that enable us to gain more insight into processing in the earliest stages of the visual system.
Room: 1.115
Email
|
|
I'm working with satellite and aerial images and try to detect trees and their species within them. For this task I use different neural networks. Currently, I focus on detecting tree species in satellite image time series - data that has a very coarse spatial, but good temporal and spectral resolution. The final goal is to create a tree species map for Germany that allows to capture the species-specific impact of climate change.
Room: 2.126
Email
|
|
I want to understand visual perception in the brain by leveraging novel machine learning techniques to build predictive models of neural population responses to natural images. Especially, I think it is important to combine a model’s predictive accuracy with interpretability to gain insights into mechanisms of biological computation. I am excited by the idea to implement the biologically inspired building blocks we develop into artificial neural networks.
Email
|
|
I am interested in finding answers for questions about how we acquire and process visual information, and how we use this information to learn. My goal is to understand how visual perception, information processing and learning works and to use this knowledge to build intelligent systems. I am working at the intersection of computer science and neuroscience by developing methods for analyzing the early visual system of the brain.
Room: 2.127
Email
|
|
I aim to comprehend how deep learning methods can be applied to unconventional data types beyond images and text, and explore generative models for these data types. Specifically, I seek to understand the effective use of deep learning in engineering design, particularly in acoustics. Additionally, I am interested in point cloud processing and its applications in forest inventory. My goal is to investigate these topics in a way that combines the power of deep learning with practical applications.
Room: 1.116
Email
|
|
I'm passionate about applied deep learning and its potential to solve real-world challenges. My current focus lies in the domain of bioacoustics, where I'm working on my master thesis project in cooperation with the German Primate Centre. Specifically, I'm studying deep learning techniques to detect, segment and classify vocalizations of ring-tailed lemurs from large-scale audio recordings.
|
|
Biologists conducted social learning experiments with free-ranging red-fronted lemurs. However, analyzing the videos manually proved to be challenging and time-consuming. Consequently, I want to use deep learning techniques to detect the various interactions occurring among the lemurs during the experiment.
|
|
I am working on a modern approach of bee monitoring in agriculture, which is currently being done manually. My goal is to use cameras to record and neural networks to detect and classify bees and other insects to get a better understanding of their population.
|
|
I am excited about developing machine learning methods that help us understand complicated and high-dimensional data sets. Our current goal is to formalise what it means for data points to belong either to clusters or to a continuum, and to develop methods for quantifying the degree of clustering. Another project I am working on is developing a representation learning method for molecular graphs, where the representation is invariant, but an equivalent object can be recovered with high probability.
Email
|