Malte Esders

Malte Esders

Auto-generated profile, based on publicly available information

Malte Esders

Machine Learning Group Technische Universität Berlin 10587 Berlin Germany

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
JKJacob Kauffmann
Jacob Kauffmann
MEMalte Esders
Malte Esders
LRLukas Ruff
Lukas Ruff
GMGrégoire Montavon
Grégoire Montavon
WSWojciech Samek
Wojciech Samek
KMKlaus-Robert Müller
Klaus-Robert Müller
A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems, however, the label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks—or “neuralized.” Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.

4 September 2020 in Science Advances
Verified
Journal Article
Open access
PDF file
PLPhilipp Leinen
Philipp Leinen
MEMalte Esders
Malte Esders
KSKristof T. Schütt
Kristof T. Schütt
CWChristian Wagner
Christian Wagner
KMKlaus-Robert Müller
Klaus-Robert Müller
FTF. Stefan Tautz
F. Stefan Tautz
Intelligent learning agent controls a scanning probe microscope and masters a nanoscale robotic task of molecule manipulation.

10 January 2025 in Journal of Chemical Theory and Computation
Verified
Journal Article
Open access
MEMalte Esders
Malte Esders
TSThomas Schnake
Thomas Schnake
JLJonas Lederer
Jonas Lederer
AKAdil Kabylda
Adil Kabylda
GMGrégoire Montavon
Grégoire Montavon
KMKlaus-Robert Müller
Klaus-Robert Müller
While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a test set alone is not a guarantee for robust chemical modeling such as stable molecular dynamics (MD). To go beyond accuracy, we use explainable artificial intelligence (XAI) techniques to develop a general analysis framework for atomic interactions and apply it to the SchNet and PaiNN neural network models. We compare these interactions with a set of fundamental chemical principles to understand how well the models have learned the underlying physicochemical concepts from the data. We focus on the strength of the interactions for different atomic species, how predictions for intensive and extensive quantum molecular properties are made, and analyze the decay and many-body nature of the interactions with interatomic distance. Models that deviate too far from known physical principles produce unstable MD trajectories, even when they have very high energy and force prediction accuracy. We also suggest further improvements to the ML architectures to better account for the polynomial decay of atomic interactions.

29 December 2023 in Computers & Chemical Engineering
Verified
Journal Article
Closed access
MEMalte Esders
Malte Esders
GRGimmy Alex Fernandez Ramirez
Gimmy Alex Fernandez Ramirez
MGMichael Gastegger
Michael Gastegger
SSSatya Swarup Samal
Satya Swarup Samal

11 January 2024 in arXiv
Verified
Preprint
Open access
PDF file
MEMalte Esders
Malte Esders
GRGimmy Alex Fernandez Ramirez
Gimmy Alex Fernandez Ramirez
MGMichael Gastegger
Michael Gastegger
SSSatya Swarup Samal
Satya Swarup Samal
Idealized first-principles models of chemical plants can be inaccurate. An alternative is to fit a Machine Learning (ML) model directly to plant sensor data. We use a structured approach: Each unit within the plant gets represented by one ML model. After fitting the models to the data, the models are connected into a flowsheet-like directed graph. We find that for smaller plants, this approach works well, but for larger plants, the complex dynamics arising from large and nested cycles in the flowsheet lead to instabilities in the solver during model initialization. We show that a high accuracy of the single-unit models is not enough: The gradient can point in unexpected directions, which prevents the solver from converging to the correct stationary state. To address this problem, we present a way to fine-tune ML models such that initialization, even with very simple solvers, becomes robust.

5 July 2021
Verified
Conference Paper
Closed access
TETaner Esat
Taner Esat
MKMarvin Knol
Marvin Knol
PLPhilipp Leinen
Philipp Leinen
MGMatthew F. B. Green
Matthew F. B. Green
MEMalte Esders
Malte Esders
FTF. Stefan Tautz
F. Stefan Tautz
The assembly of single-molecule devices with the help of the manipulation capability of scanning probe microscopes offers many opportunities for quantum- and nanotechnology. A key challenge is fabricating device structures that can overcome their attraction to the underlying surface and thus protrude from the two-dimensional flatlands of the surface. In my talk, I will report the fabrication of such a structure: we use the tip of a scanning probe microscope to lift a large planar aromatic molecule into an upright, standing geometry on a pedestal of two metal adatoms. This atypical upright orientation of the single molecule, whose stability can be understood as the result of a fine balance between chemical and dispersion forces, enables the system to function as a quantum dot and an on-demand coherent single-electron field emitter. If attached to the tip of the microscope, the standing molecule can also be applied as a sensitive quantum dot sensor. We anticipate that other metastable adsorbate configurations might also be accessible, thereby opening up the third dimension for the design of functional nanostructures on surfaces. Finally, we have made first steps into the direction of an autonomous robotic nanofabrication of single-molecule devices.