activity
20102022
most citedActivation Functions in Artificial Neural Networks: A Systematic Overview

47 citations · 76 across the 13 of their papers we have counts for

collaborators

21 papers

stat.ML2022

VC-PCR: A Prediction Method based on Supervised Variable Selection and Clustering

Rebecca Marion, Johannes Lederer, Bernadette Govaerts +1

Sparse linear prediction methods suffer from decreased prediction accuracy when the predictor variables have cluster structure (e.g. there are highly correlated groups of variables…

q-bio.GN2022

Depth Normalization of Small RNA Sequencing: Using Data and Biology to Select a Suitable Method

Yannick Düren, Johannes Lederer, Li-Xuan Qin

Deep sequencing has become one of the most popular tools for transcriptome profiling in biomedical studies. While an abundance of computational methods exists for "normalizing" seq…

cs.LG20211 cited

Copula-Based Normalizing Flows

Mike Laszkiewicz, Johannes Lederer, Asja Fischer

Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations. But their expressi…

cs.LG2021

Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks

Leni Ven, Johannes Lederer

Deep learning requires several design choices, such as the nodes' activation functions and the widths, types, and arrangements of the layers. One consideration when making these ch…

cs.LG2021

Targeted Deep Learning: Framework, Methods, and Applications

Shih-Ting Huang, Johannes Lederer

Deep learning systems are typically designed to perform for a wide range of test inputs. For example, deep learning systems in autonomous cars are supposed to deal with traffic sit…

stat.ML2021

DeepMoM: Robust Deep Learning With Median-of-Means

Shih-Ting Huang, Johannes Lederer

Data used in deep learning is notoriously problematic. For example, data are usually combined from diverse sources, rarely cleaned and vetted thoroughly, and sometimes corrupted on…