Helmholtz Imaging CONNECT

Go back Home Experts L. Klein

MR. Lukas Klein

German Cancer Research Center, ETH Zürich

Skills:
Explanatory Methods, Interpretable Representation-learning, Model uncertainty, Probabilistic AI, Bayesian NN
Projects:
Improving Explainability through Disentangled Feature Representation, XAI in Multiple Instance Learning, Explaining Model-Uncertainty

Send mail to Lukas Klein (lukas.klein@dkfz-heidelberg.de)

mail form

Mail sender *

Mail subject *

Mail text *

Send a copy of my message to my own e-mail address.

©Lukas Klein

Deutsches Krebsforschungszentrum - Heidelberg

Weblinks

Git
X (Twitter)
LinkedIn

Lukas Klein in Helmholtz Imaging CONNECT:

Application

Explainable AI

Explainable AI (XAI) aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 4 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 4 ➤Solutions: 1

Application

Probabilistic Modeling

Machine Learning and Statistics, based on the bayesian premise that parameters are random variables. Enables generative models, density estimation, and uncertainty quantification.

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 2 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 2 ➤Solutions: 0

No modality found.

No facility found.

Center

Deutsches Krebsforschungszentrum (DKFZ)

More than 450,000 people are diagnosed with cancer each year in Germany. Cancer is a disease that poses enormous challenges to research, because every cancer is different and its course can vary immensely even from …

In Helmholtz Imaging CONNECT
➤Applications: 25 ➤Facilities: 0 ➤Instruments: 6 ➤Labs: 11 ➤Modalities: 24 ➤Experts: 21 ➤Solutions: 9

No instrument found.

Lab

Interactive Machine Learning (IML)

Considering human interaction when designing machine learning (ML) systems bears great potential: On the one hand, decision-making in ML systems remains imperfect in practice, thus requiring human interaction for safety-critical applications such as clinical diagnostics. …

In Helmholtz Imaging CONNECT
➤Applications: 0 ➤Facilities: 0 ➤Centers: 2 ➤Instruments: 0 ➤Modalities: 0 ➤Experts: 4 ➤Solutions: 2

Solution

Multi-path Explanations Library (m-pax_lib)

This repository contains a framework which allows for enhanced model interpretability and model robustness. The framework utilizes interpretable disentangled representations for downstream-task prediction which are in a second step visualized and evaluated through a multipath-attribution …

In Helmholtz Imaging CONNECT
➤Applications: 1 ➤Facilities: 0 ➤Centers: 1 ➤Instruments: 0 ➤Labs: 1 ➤Modalities: 0 ➤Experts: 2