Name: Roman Schulte-Sasse
Type: User
Company: Max Planck Institute for molecular Genetics
Bio: Computer scientist with specialization in machine learning and robotics. PhD in computational Biology where I used graph deep learning to predict cancer genes.
Twitter: SchulteRoman
Location: Berlin
Blog: schulter.github.io/
Roman Schulte-Sasse's Projects
An efficient implementation of a fully connected neural network
A phylogenetic tree to determine Covid-19 spread and sequence similarity
Unsupervised learning of DNA sequence features
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
An explainable multi-omics graph integration method based on graph convolutional networks to predict cancer genes.
Classifies german road signs by using a convolutional neural network.
Simulate networks with implanted graph motifs (cliques, stars, etc)
Detect waggle dances of bees