Am I Interested In Machine Learning?

Alexander Immer

My inquiry focuses on probabilistic motorcar learning and data scientific discipline. Currently, I am especially interested in approximate inference for neural networks and biomedical applications. I desire to design algorithms that can incorporate prior cognition, quantify uncertainty, and automatically select the most probable model given data. Peculiarly in the context of neural networks, these bug remain challenging. I accept previously worked on methods for fourth dimension series, due east.g., mobility and political information.

Amir-Hossein Karimi

I am generally interested in human behavior, how intelligence is formed in humans, and how it can be replicated in machines. As a first twelvemonth PhD student, I am exploring AI methods that are interpretable and explainable, with a focus on probabilistic inference on the organization of entities, or learning compositional and causal generative processes. My inquiry has a broad impact, potentially in three areas: (one) more than adoption of automobile learning methods in critical social, economical, and public health domains due to the added trust gained from explainable methods; (2) amend model pick strategies that point out hazardous practices with the abundance of data, including data leakage of irrelevant factors; (3) state-of-the-art models with improved fidelity/accuracy as we are able to conduct phase-wise learning of abstruse objects and concepts and then complex relationships.

Andrii Zadaianchuk

My research interests prevarication in the intersection of unsupervised structured representations learning, dynamics learning and using both for model-based reinforcement learning. I find autonomous learning of environment representations that are modular, independently predictable and controllable as an important step towards efficient and authentic control for many real-life applications.

Principal Host(south):	Georg Martius (Max Planck Institute for Intelligent Systems)
Exchange Host(s):

Cathrin Elich

My inquiry interests lie in the wide field of computer vision and, more specifically, are currently focused on learning structured scene representations. I'm interested to learn about ways in which humans perceive their environment and how to use these ideas in combination with deep learning methods. Moreover, I want to explore options of combining this work with other tasks similar segmentation or 3D reconstruction.

Primary Host(southward):	Jörg Stückler (Max Planck Institute for Intelligent Systems)
Exchange Host(southward):

Cristina Pinneri

In order to create intelligent machines, we should endow them with features connecting areas like motorcar learning and optimal control. Reinforcement learning lies at the intersection between these two areas and it will be the focus of my PhD, with a particular interest on model-based approaches and trajectory optimization.

Daniela Macari

I am interested in exploring forms of physical intelligence inspired by materials and mechanisms establish in nature and in applying these to the blueprint and fabrication of soft robotic systems. Peculiarly, my inquiry focus lies on bioinspired actuation systems replicating the versatile functioning of natural muscles - and then-called HASEL (hydraulically amplified self-healing electrostatic) actuators. This new class of electrohydraulic transducers enables the creation of novel soft robotic systems with even so unmet high degrees of dexterity, agility and adjustability to their environments, making them well-suited for unstructured and dynamic tasks.

Hamza Keurti

Generally, I am interested in creating vision systems which understand visual scenes like humans exercise and which acquire to perceive the aforementioned mode children acquire: through embodiment and costless interaction (playing) with objects. In particular, my aim is to learn robust and predictive representations from visual scenes with the integration of efferent motor signals, in the absence of tasks. An embodied agent should learn to perceive prior to learning tasks.

Julian Nubert

I am interested in robots that are non simply moving in simply actively impacting their surroundings. My principal field of research lies in the intersection of command, perception, and motorcar learning, intending to enable mobile robots to perform complex tasks. I am mainly working in the field of structure robotics, specifically on democratic digging and manipulation with a walking excavator.

Kamil Adamczewski

Electric current neural networks remain big and not fully understood. My research links network compression with model interpretability. This natural connection aims at extracting relevant data from the network while discarding the redundant parameters. This goal of reducing neural networks not only makes models faster, more practical and free energy-efficient merely too aims to analyze and translate the relevant features that make up a smaller model. We look at this problem from diverse perspectives, ranging from probabilistic to game-theoretical approaches. My further interests prevarication in information generation and differential privacy.

Mattia Segù

Current state-of-the-art machine learning models often unpredictably fail when dealing with previously unseen settings, proving to be not general and robust enough for a safe deployment in life-disquisitional applications. In the spirit of delivering safe and reliable intelligent systems, my inquiry interests focus on solving the challenges presented by the real world by making artificial intelligence models capable of continuously learning and adapting to previously unknown scenarios.

Main Host(s):
Exchange Host(south):	Bernt Schiele (Max Planck Constitute for Informatics & Saarland University)

Max Paulus

I take a broad involvement in machine learning, including variational methods, causal inference and probabilistic programming. In the futurity, I hope to pattern adaptive machines that leverage prior knowledge to effectively learn in domains where traditional approaches still fail today.

Maximilian Mordig

After a Bachelor'southward in Physics and Master's in "Computational Science & Engineering" at EPFL, I worked for Hoffmann-La Roche for roughly ii years. My PhD, supervised past Bernhard Schölkopf and Gunnar Rätsch, will focus on causal inference, representation learning and applications to biological datasets. I previously worked on Bayesian optimization, variational inference and Gaussian processes. The dazzler of probabilistic modelling thrills me.

Muhammed Kocabas

I am interested in reckoner vision and machine learning with a focus on human being movement understanding.

Nadine Rüegg

My enquiry focuses on interaction between humans and their environment, 3D pose and tracking. I hope past combining computer vision and machine learning methods, a holistic understanding of video scenes can be obtained.

Nicolò Ruggeri

My research interests include, but are not limited to, Probabilistic Learning and Network Science, every bit well as connected fields. In detail, I aim at agreement how current probabilistic models tin be improved upon, both on a representation and training level. I am also fascinated by how unlike ideas and concepts from inside and outside ML interpolate in interesting and novel developments. Therefore, I strive to keep a broader view on theoretical and practical insights originating from different fields.

Nima Mahkam

My research interests prevarication in developing flexible and intelligent microrobots as a promising potential approach in medical applications. I am mainly interested in fabricating modest-scale mechanisms and characterizing their properties to empathise the microscale dynamics better. Analyzing these tiny robots' beliefs and identifying their mechanical and biocompatible characteristics are crucial for precisely controlling these micro-mechanisms in tight environments such equally the human body. Consequently, my studies aim to explore new blueprint approaches, fabrication techniques, and control principles for intelligent soft small robots, which would have a loftier impact in healthcare.

Núria Armengol Urpí

Despite contempo advances in robotics, the gap between human and robot skills remains vast. During my PhD I aim to combine the tools from machine learning and command theory in guild to advance in the field of democratic learning for robotics. I endeavour to develop algorithms that provide robots with the ability to efficiently explore new environments and autonomously learn from diverse prior data, then that they can intelligently, reliably and robustly handle the complexities of the existent world.

Olga Mineeva

I am interested in developing robust and interpretable Automobile Learning methods for real-globe problems, in particular, that ascend in Healthcare and Genomics.

Paul Wrede

My aim is to blueprint microscale robots to revolutionize the treatment and diagnosis of diseases. Too designing the next generation of smart microrobots I am specially interested in visualizing these tiny human-made machines in-vivo. Consequently, my enquiry interests include microrobotics, bioimaging, and micro/nanotechnologies as well every bit personalized medicine.

Philippe Wenk

My inquiry focuses on leveraging motorcar learning methods to model and control fourth dimension continuous dynamical systems. Inspired past traditional scientific parametric model building, I am working on developing novel strategies for reinforcement learning, system identification and control.

Sidak Pal Singh

My enquiry focuses on the broad areas of deep learning theory, optimization, and causal representation learning. In particular, I am interested in understanding and answering: (a) why over-parameterized neural networks generalize so well (b) how to comprise (causal) mechanisms to encourage generalization in the non-iid setting. I also like to utilize tools and perspectives from mathematical areas, such as optimal transport, for budgeted problems in automobile learning.

Siyeon Jang

I am interested in tiny medical robots that can generate localized electric field stimulation. Since electric fields tin can touch various biological interactions, such wireless nano/micro-scale robots are expected to be one of the about promising strategies to achieve constructive medical applications.

Songyou Peng

My full general enquiry interest lies in computer vision and machine learning. More than specifically, I am interested in how to utilize deep learning to 3D vision problems.

Primary Host(s):
Commutation Host(s):	Andreas Geiger (Academy of Tübingen & Max Planck Plant for Intelligent Systems)

Timothy Gebhard

Mostly, in my research, I am interested in issues at the intersection of auto learning and domain sciences (in detail, astrophysics). More specifically, I want to investigate how we can incorporate and make use of existing scientific domain knowledge near a given trouble to build ameliorate auto learning models. One specific project that I am currently working on aims to develop new ML-based post-processing algorithms for high-contrast imaging of extrasolar planets.

Vasileios Choutas

I am interested in modelling the human trunk, its movement and interaction with objects and scenes, which could then be used to generate new human-like actions and behavior for virtual agents.

Xu Chen

My inquiry interest lies in computer vision and graphics. Specifically I am interested in 3D deep generative models, with a goal to build learning-based approaches capable of generating photo-realistic simulations of human being activity. The resulting data could be useful in the context of training methods for human-axial perception tasks.

Yao Feng

My master research is at the intersection between Estimator Vision, Calculator Graphics and Machine Learning, with a focus on understanding 3-dimensional objects using deep learning technique. Currently, I am especially interested in the modeling and analysis of homo faces and bodies.

Yufeng Zheng

My general research involvement lies in the intersection of estimator vision and graphics. More specifically, I'1000 interested in learning-based 3D modelling and assay for homo-axial applications.

Yuntao Ma

Controlling mobile manipulators in hard environments is challenging and exciting. During my Ph.D., I aim to expand the capability of mobile manipulators with reinforcement learning and demonstrate the results on existent machines. Currently, I work on combining control policies for complex tasks.

Source: https://learning-systems.org/phds

Posted by: wrightafron1953.blogspot.com