Banner Banner

Dr. Robert Vandermeulen

Icon

Technische Universität Berlin
Machine Learning / Intelligent Data Analysis (IDA)

Marchstr. 23, 10587 Berlin
https://www.tu.berlin/en/ml

Robert Vandermeulen Bifold researcher
© Vandermeulen

Dr. Robert Vandermeulen

Postdoctoral Researcher

Dr. Robert Vandermeulen is a Postdoctoral Researcher at BIFOLD. He earned his PhD in Electrical Engineering at the University of Michigan in 2016. Prior to working at BIFOLD Robert was a postdoctoral researcher at Technische Universität Kaiserslautern. His work focuses on deep anomaly detection and nonparametric statistics.

  • Deep Anomaly Detection
  • Nonparametric Density Estimation
  • Nonparametric Tensor Methods
  • Nonparametric Statistics
  • Human vs. Neural Network Alignment
     

Lukas Muttenthaler, Lorenz Linhardt, Jonas Dippel, Robert A. Vandermeulen, Katherine Hermann, Andrew K. Lampinen, Simon Kornblith

Improving neural network representations using human similarity judgments

September 26 , 2023
https://arxiv.org/pdf/2306.04507.pdf

Lukas Muttenthaler, Robert A. Vandermeulen, Qiuyi Zhang, Thomas Unterthiner, Klaus-Robert Müller

Set Learning for Accurate and Calibrated Models

July 10 , 2023
https://arxiv.org/pdf/2307.02245.pdf

Lukas Muttenthaler, Jonas Dippel, Lorenz Linhardt, Robert A. Vandermeulen, Simon Kornblith

Human alignment of neural network representations

2023
https://arxiv.org/abs/2211.01201

Lukas Muttenthaler, Charles Yang Zheng, Patrick McClure, Robert A. Vandermeulen, Martin N. Hebart, Francisco Pereira

VICE: Variational Interpretable Concept Embeddings

October 06 , 2022
https://arxiv.org/abs/2205.00756

News
Machine Learning| Dec 21, 2021

Lifting the curse of dimensionality for statistics in ML

The paper “Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation” by BIFOLD researcher Dr. Robert A. Vandermeulen and his colleague Dr. Antoine Ledent, Technical University Kaiserslautern, was presented at the Conference on Neural Information Processing Systems (NeurIPS 2021). Their paper provides the first solid theoretical foundations for applying low-rank methods to nonparametric density estimation.