Machine learning investigates and develops methods that allow computers to infer or recognize patterns using datasets of various sizes, whether for exploratory purposes or to accomplish specific tasks. It has applications in numerous areas, from information systems and bioinformatics to computer vision, robotics, and security, among others.
Groups and Researchers in this Field
Algorithms & Inequality
Rediet Abebe is a junior fellow at the Harvard Society of Fellows and an Andrew Carnegie Fellow. Her research examines the interaction of algorithms and inequality, with a focus on contributing to the scientific foundations of this area. Abebe has also co-founded numerous organizations, including the ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), and the associated international research initiative. Abebe is the recipient of numerous awards and honours, including the Hector Endowed Fellowship by the European Laboratory for Learning and Intelligent Systems (ELLIS), MIT Technology Fellows 35 Innovators under 35, the ACM SIGKDD Dissertation Award, and an honorable mention for the ACM SIGecom Dissertation Award. Abebe is currently leading several large-scale evaluations of ML systems used in commercial, legal, and policy contexts. Read more
Laurent Bindschaedler is a Research Group Leader at the Max Planck Institute for Software Systems, where he leads the Data Systems Group (DSG). Focused on applications, his group explores a wide range of topics at the intersection of systems, data management, and machine learning, such as systems for big data and machine learning, machine learning for systems, real-time analytics systems, and decentralized systems like blockchains. Laurent is known for building the Chaos graph processing system, which holds a record for the largest graph processed on a small cluster of commodity servers. The Data Systems Group is dedicated to advancing the field of data systems by developing innovative methods, tools, and technologies to manage and analyze large-scale data sets, thereby empowering organizations and researchers to unlock the full potential of their data for innovation, improved decision-making, and complex problem-solving.
Read more
Michael J. Black is one of the founding directors of the Max Planck Institute for Intelligent Systems, where he leads the Perceiving Systems Department. His research addresses a variety of topics relating to computer vision and perception: the statistics of natural scenes and their motion; articulated human motion pose estimation and tracking; the estimation of human body shape from images and video; the representation and detection of motion discontinuities; and the estimation of optical flow. His early work on optical flow has been widely used in Hollywood films. He also does research on neural engineering for brain-machine interfaces and neural prostheses. He is an honorary professor at the University of Tübingen, visiting professor at ETH Zürich, and adjunct professor (research) at Brown University. Read more
Karsten Borgwardt is a director at the MPI for Biochemistry. His research focuses on the fields of bioinformatics, biomarker discovery and personalized medicine.
In the Machine Learning and Systems Biology department, big data analysis and biomedical research meet: They develop novel data mining algorithms to detect patterns and statistical dependencies in large datasets from biology and medicine. The group is working towards two central goals: To enable the automatic generation of new knowledge from big data through machine learning, and to gain an understanding of the relationship between the function of biological systems and their molecular properties. Read more
Wieland leads the Robust Machine Learning group at the Max Planck Institute for Intelligent Systems. In the past few years, deep neural networks have surpassed human performance on a range of complex cognitive tasks. However, unlike humans, these models can be derailed by almost imperceptible perturbations, often fail to generalise beyond the training data and require large amounts of data to learn novel tasks. The core reason for this behaviour is shortcut learning, i.e. the tendency of neural networks to pick up statistical signatures sufficient to solve a given task instead of learning the underlying causal structures and mechanisms in the data. Our research ties together adversarial machine learning, disentanglement, interpretability, self-supervised learning, and theoretical frameworks like nonlinear Independent Component Analysis to develop theoretically grounded yet empirically successful visual representation learning techniques that can uncover the underlying structure of our visual world and close the gap between human and machine vision. Read more
Meeyoung Cha is a scientific director of MPI-SP in Bochum, Germany. Her interests include data science and computational social science, with a focus on understanding social information and human-machine interactions. Meeyoung’s research on misinformation, poverty mapping, fraud detection, and long-tail content has received wide citations and best paper awards. She is the recipient of the Korean Young Information Scientist Award 2019, the AAAI ICWSM Test-of-Time! Award 2020, and the ACM IMC Test-of-Time Award 2022. Prior to joining MPI, Meeyoung was a chief investigator at IBS (2019-current), a faculty member at KAIST (2010-current), a visiting professor at Facebook (2015-2016), and a postdoctoral researcher at MPI-SWS (2008-2010). She received her Ph.D. in computer science from KAIST in 2008. Read more
Peter Dayan is a Director of the Max Planck Institute for Biological Cybernetics. His research focuses on decision-making processes in the brain, the role of neuromodulators as well as neuronal malfunctions in psychiatric diseases. Dayan has long worked at the interface between natural and engineered systems for learning and choice, and is also regarded as a pioneer in the field of Artificial Intelligence. Read more
Peter Dayan
MPI for Biological Cybernetics, Scientific Director Personal Website
Physics for Inference and Optimization
Caterina de Bacco is an Independent Research Group Leader at the Max Planck Institute for Intelligent Systems in Tübingen. She is interested in understanding, optimizing and predicting relations between the microscopic and macroscopic properties of complex large-scale interacting systems. She likes to approach research by addressing application-oriented problems involving domain experts from different disciplines via developing models and algorithms derived from statistical physics principles. She studies large interacting systems following two main research directions---inference on networks and routing optimization on networks. Read more
Jonas Geiping leads a joint research group at the Max Planck Institute for Intelligent Systems and the ELLIS Institute Tübingen. His group is interested in questions of safety and efficiency in modern machine learning. There are a number of fundamental machine learning questions that come up in these topics that we still do not understand well. In safety, examples are questions about the principles of data poisoning, the subtleties of water-marking for generative models, privacy questions in federated learning, or adversarial attacks against large language models. Can we ever make these models “safe”, and how do we define this? Are there feasible technical solutions that reduce harm?
Further, the research group is interested in questions about the efficiency of modern AI systems, especially for large language models. How efficient can we make these systems, can we train strong models with little compute? Can we extend the capabilities of language models with recursive computation? How do efficiency modifications impact the safety of these models? Read more
Manuel Gomez Rodriguez is interested in developing machine learning and large-scale data mining methods for analysis and modeling of large real-world networks and processes that take place over them. His research comprises several dimensions: developing models of these networks and processes, assessing their theoretical properties and limitations; developing machine learning algorithms to fit the models and computational methods to influence processes over networks; and validating models and methods on gigabite- and terabyte-scale real-world datasets. Ultimately, he aims to provide computational tools with applications in a variety of domains, e.g. social and information sciences, economics, decision theory, causality, and epidemiology. Read more
Krishna Gummadi heads the Social Computing research group at the Max Planck Institute for Software Systems. He is broadly interested in understanding and building networked and distributed computer systems. Currently, the group's research focuses on social computing systems: an emerging class of societal-scale human-computer systems that facilitate interactions and knowledge exchange between individuals, organizations, and governments in our society. A few examples include social networking sites like Facebook, blogging and microblogging sites like LiveJournal and Twitter, and content sharing sites like YouTube, among many others. Through user studies, examining data, and building systems, the group aims to understand, predict, and control the behavior of their constituent human users and computer systems. Read more
Moritz Hardt is a scientific director at the Max Planck Institute for Intelligent Systems, where he leads the Social Foundations of Computation Department. His research contributes to the scientific foundations of machine learning and algorithmic decision making with a focus on social questions. His research interests span four areas: (1) Applying machine learning in social and economic contexts, (2) formulating social and dynamic actions as mathematical models, (3) examining the validity and reliability of statistical methods and the construction of datasets within scientific communities, and (4) the pursuit of normative goals, and in particular, how to formulate values and norms mathematically. Hardt is co-founder of the conference "Fairness, Accountability, and Transparency in Machine Learning." He is co-author of "Fairness and Machine Learning: Limitations and Opportunities" (MIT Press, 2022) and "Patterns, Predictions, and Actions: A Story About Machine Learning" (Princeton University Press, 2022). Read more
The research focus of Prof. Dr. Thomas Hofmann, who is a Max Planck Fellow at the MPI for Intelligent Systems, lies on deep learning – on its mathematical foundations as well as its applications. This includes contributions to optimization for machine learning, but also investigations into specific topics such as normalization and regularization techniques and understanding of generative models. Hofmann is one of the leading AI scientists in Europe, displaying a unique blend of theoretically principled yet often highly applicable research, and a track record for pioneering fields. At the MPI-IS in Tübingen, Hofmann leads a group on Coordinative Intelligence. The group interprets intelligence as a coordinative and communicative process. Read more
Andreas Krause is a Max Planck Fellow at the Max Planck Institute for Intelligent Systems in Tübingen. Krause pursues a wide range of topics in machine learning, reinforcement learning and AI. His goal is to “bridge the gap,” developing new theory and algorithms with guarantees, and demonstrating their utility on interdisciplinary applications ranging from computational sustainability to robotics to experimental design to information gathering on the web. A central focus of his group is on computational foundations of reasoning under uncertainty and reliable data-driven decision-making. Read more
Celestine Mendler-Dünner is a research group leader at MPI-IS, a Principal Investigator at the ELLIS Institute Tübingen, and a faculty member of the Tübingen AI Center. Her research spans machine learning, prediction and algorithmic decision-making with a focus on the societal embedding of technology, broadly scoped. She pursues theoretical as well as empirical questions that shed light on how data-driven systems interact with society, and how to build reliable systems in dynamic environments. She obtained her PhD from ETH Zurich in computer science and before moving to Tübingen she spent two years as a SNSF postdoctoral fellow at UC Berkeley. Her research contributions have been recognized with the ETH Medal, the Fritz Kutter Prize and the IBM Eminence and Excellence award. She is a fellow of the Elisabeth Schiemann Kolleg, and a member of the Tübingen Cluster of Excellence on ML for Science. Read more
Michael Muehlebach is leading the independent research group Learning and Dynamical Systems at the Max Planck Institute for Intelligent Systems in Tuebingen, Germany. He is interested in a wide variety of subjects, including machine learning, dynamics, control, and optimization. Some of his recent work deals with large-scale constrained optimization in a machine learning context, stochastic minimax optimization, adaptive decision-making and reinforcement learning. While rigorous theory and mathematical analysis forms the basis of his research, he also likes to evaluate his algorithms in experiments with real-world cyber-physical or robotic systems, such as balancing robots or flying vehicles. Throughout his career Michael has received numerous awards, such as the ETH Medal and the HILTI prize for innovative research, and he was awarded the Branco Weiss and Emmy Noether Fellowship. Read more
Gerard Pons-Moll is the head of the Emmy Noether independent research group "Real Virtual Humans" and senior researcher at the Max Planck for Informatics (MPII) in Saarbrücken. His research lies at the intersection of computer vision, machine learning and computer graphics -- with special focus on analyzing people in videos, and creating virtual human models by "looking" at real ones. His research has produced some of the most advanced statistical human body models of pose, shape, soft-tissue and clothing, as well as algorithms to track and reconstruct 3D people models from images, video, depth, and IMUs. His work has received several awards including the prestigious Emmy Noether Grant (2018), a Google Faculty Research Award (2019), a Facebook Reality Labs Faculty Award (2018), and recently the German Pattern Recognition Award (2019), and several best paper awards. Read more
Goran Radanović is a research group leader at the Max Planck Institute for Software Systems. He is generally interested in studying AI systems, and more specifically in the design and analysis of systems with intelligent and self-interested agents. Particular topics of his research interest include value-aligned artificial intelligence, human-AI collaboration, and decision making systems with societally-aware utility functions. His research utilizes tools from game theory (esp. mechanism design), machine learning (esp. reinforcement learning), and human-centered AI (esp. crowdsourcing). His work covers both theoretical and practical aspects of problem instances related to his research topics. Read more
Iyad Rahwan is a scientific director at the Max Planck Institute for Human Development, where he leads the Center for Humans & Machines. He is also an honorary professor of Electrical Engineering and Computer Science at the Technical University of Berlin. Previously, he was an Associate Professor of Media Arts & Sciences at the Massachusetts Institute of Technology (MIT). Rahwan's work lies at the intersection of computer science and human behavior, with a focus on the impact of Artificial Intelligence on society. His work appeared in major academic journals, including Science and Nature. Read more
Samira Samadi is a research group leader at the Max Planck Institute for Intelligent Systems. Her research background is in machine learning and algorithm design with a recent focus on optimizing human ML teaming. She studies the interactions between humans and ML and uses her findings to design hybrid ML systems that augment humans’ abilities rather than replace them. Most of the questions that she studies are inspired by medical applications and public health. Read more
Bernt Schiele is the founder of the Computer Vision and Multimodal Computing Department at the Max Planck Institute for Informatics, and head of its Computer Vision research area. His group focuses on multimodal sensor processing as well as computer vision. In computer vision, they consider problems of 3D understanding of images and video, such as object class recognition, people detection and tracking, and understanding traffic scenes. In multimodal computing, they are focusing on human activity recognition as a means to study how ubiquitous or wearable computing may benefit from better sensor understanding. Their research also involves machine learning, which is instrumental to inferring higher-level information from noisy sensor data and handling large-scale multimodal databases and sensor streams. Read more
Bernhard Schölkopf directs the Empirical Inference Department at the Max Planck Institute for Intelligent Systems. The department investigates problems of empirical inference, i.e. inference based on empirical data. The type of inference can vary, including for instance inductive learning (estimation of models such as functional dependencies that generalize to novel data sampled from the same underlying distribution), or the inference of causal structures from statistical data (leading to models that provide insight into the underlying mechanisms, and make predictions about the effect of interventions). Empirical data may also vary, from sparse experimental measurements (e.g. microarray data) to visual patterns. The department uses theoretical, algorithmic, and experimental approaches to study these problems. Read more
Adish Singla is a faculty member at the Max Planck Institute for Software Systems. He is interested in the design of AI-ML methods that interact with, learn from, and teach other learning entities such as humans, robots, and machines. His research interests span various application domains, including the design of intelligent tutoring systems for personalized education, social robotics, and adversarial machine learning. The theoretical aspects of his work include machine learning (esp. online, active), AI (esp. probabilistic modeling), and optimization (esp. submodular). The focus is towards designing principled techniques that are both theoretically well-founded with strong provable guarantees and are practically applicable. Read more
Mariya Toneva’s research is at the intersection of Machine Learning, Natural Language Processing, and Neuroscience. Her group bridges language in machines with language in the brain, with a focus on building computational models of language processing in the brain that can also improve natural language processing systems. Prior to joining MPI-SWS, she is conducting research as a C.V. Starr Fellow at the Princeton Neuroscience Institute. She received her Ph.D. in a joint program between Machine Learning and Neural Computation from Carnegie Mellon University. Read more
