Lukas Muttenthaler
Lukas Muttenthaler
Doctoral Researcher
Since 2021 Lukas is a Ph.D. student in the Machine Learning Group at Technische Universität Berlin and a full-time researcher at the Berlin Institute for the Foundations of Learning and Data (BIFOLD). In addition, Lukas is a guest researcher at the Max Planck Institute (MPI) for Human Cognitive and Brain Sciences in Leipzig where he was employed before. Lukas is currently part of a research collaboration program with Google Brain. Prior to his time at the MPI, Lukas did a Master's in IT and Cognition / Computer Science at the University of Copenhagen. His research is supported by additional funding from Google.
Lukas’ research mainly revolves around representation learning in computer vision. He works at the intersection of Machine Learning and Cognitive Science, where he is mostly interested in the question of how human inductive biases can be leveraged to benefit machine learning algorithms.
- Representation Learning
- Few-shot Learning
- Probabilistic Methods
- Variational Inference
- Cognitive Science
Frieda Born, Tom Neuhäuser, Lukas Muttenthaler, Brett D Roads, Bernhard Spitzer, Andrew Kyle Lampinen, Matt Jones, Klaus Robert Muller, Michael Curtis Mozer
Context Sensitivity Improves Human-Machine Visual Alignment
Laure Ciernik, Lorenz Linhardt, Marco Morik, Jonas Dippel, Simon Kornblith, Lukas Muttenthaler
Objective drives the consistency of representational similarity across datasets
Lukas Muttenthaler
Representational alignment of humans and machines for computer vision
Laure Ciernik, Lorenz Linhardt, Marco Morik, Jonas Dippel, Simon Kornblith, Lukas Muttenthaler
Training objective drives the consistency of representational similarity across datasets
Lukas Muttenthaler, Klaus Greff, Frieda Born, Bernhard Spitzer, Simon Kornblith, Michael C. Mozer, Klaus-Robert Müller, Thomas Unterthiner, Andrew K. Lampinen
Aligning Machine and Human Visual Representations across Abstraction Levels
Researcher Spotlight: Dr. Lukas Muttenthaler
What if AI could learn to see the world the way we do? BIFOLD PhD graduate Dr. Lukas Muttenthaler is pushing AI beyond raw performance, exploring representational alignment, where cognitive science meets computer vision to build machines that perceive more like humans.
When AI “thinks” like us
A team of researchers from BIFOLD, Google DeepMind, Max Planck Institute for Human Development and Max Planck Institute for Cognitive and Brain Sciences developed a new approach for image processing models, „AligNet“, that for the first time integrates human semantic structures into neural image processing models, bringing the visual understanding of these computer models closer to that of humans. Their publication „Aligning Machine and Human Visual Representations across Abstraction Levels“ has now been published in the prestigious scientific journal „Nature“.
BIFOLD researchers present three papers at ICLR 2024
The International Conference on Learning Representations (ICLR) is a Core-A gathering of experts who are dedicated to advancing a branch of artificial intelligence known as representation learning, which is also called deep learning.
Do computers and humans "see" alike?
The field of computer vision has long since left the realm of research and is now used in countless daily applications, such as object recognition and measuring geometric structures of objects. One question that is not or only rarely asked is: To what extent do computer vision systems see the world in the same way that humans do?