b'Asja Fischer'

research

∙ 07/13/2023

Layerwise Linear Mode Connectivity

In the federated setup one performs an aggregation of separate local mod...

0 Linara Adilova, et al. ∙

research

∙ 05/26/2023

Leveraging characteristics of the output probability distribution for identifying adversarial audio examples

Adversarial attacks represent a security threat to machine learning base...

0 Matías P. Pizarro B., et al. ∙

research

∙ 05/22/2023

Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation

State-of-the-art deep neural networks have proven to be highly powerful ...

0 Kira Maag, et al. ∙

research

∙ 03/01/2023

Information Plane Analysis for Dropout Neural Networks

The information-theoretic framework promises to explain the predictive p...

0 Linara Adilova, et al. ∙

research

∙ 10/26/2022

Towards the Detection of Diffusion Model Deepfakes

Diffusion models (DMs) have recently emerged as a promising method in im...

0 Jonas Ricker, et al. ∙

research

∙ 06/21/2022

Marginal Tail-Adaptive Normalizing Flows

Learning the tail behavior of a distribution is a notoriously difficult ...

0 Mike Laszkiewicz, et al. ∙

research

∙ 04/22/2022

How Sampling Impacts the Robustness of Stochastic Neural Networks

Stochastic neural networks (SNNs) are random functions and predictions a...

0 Sina Däubener, et al. ∙

research

∙ 12/14/2021

Robustifying automatic speech recognition by extracting slowly varying features

In the past few years, it has been shown that deep learning systems are ...

0 Matias Pizarro, et al. ∙

research

∙ 07/15/2021

Copula-Based Normalizing Flows

Normalizing flows, which learn a distribution by transforming the data t...

0 Mike Laszkiewicz, et al. ∙

research

∙ 01/07/2021

A Novel Regression Loss for Non-Parametric Uncertainty Optimization

Quantification of uncertainty is one of the most promising approaches to...

0 Joachim Sicking, et al. ∙

research

∙ 12/23/2020

Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties

Quantification of uncertainty is one of the most promising approaches to...

0 Joachim Sicking, et al. ∙

research

∙ 08/07/2020

Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification

Uncertainty quantification in neural networks gained a lot of attention ...

0 Sina Däubener, et al. ∙

research

∙ 07/19/2020

Improving the Long-Range Performance of Gated Graph Neural Networks

Many popular variants of graph neural networks (GNNs) that are capable o...

0 Denis Lukovnikov, et al. ∙

research

∙ 07/10/2020

Characteristics of Monte Carlo Dropout in Wide Neural Networks

Monte Carlo (MC) dropout is one of the state-of-the-art approaches for u...

0 Joachim Sicking, et al. ∙

research

∙ 06/26/2020

On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions

The Metropolis algorithm is arguably the most fundamental Markov chain M...

0 Kai Brügge, et al. ∙

research

∙ 05/24/2020

Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification

Machine learning systems and also, specifically, automatic speech recogn...

0 Sina Däubener, et al. ∙

research

∙ 05/15/2020

Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency

In recent years generative adversarial network (GAN) based models have b...

0 Mohammad Asif Khan, et al. ∙

research

∙ 05/01/2020

Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery

The graphical lasso is the most popular estimator in Gaussian graphical ...

0 Mike Laszkiewicz, et al. ∙

research

∙ 03/19/2020

Leveraging Frequency Analysis for Deep Fake Image Recognition

Deep neural networks can generate images that are astonishingly realisti...

24 Joel Frank, et al. ∙

research

∙ 02/25/2020

End-to-End Entity Linking and Disambiguation leveraging Word and Knowledge Graph Embeddings

Entity linking - connecting entity mentions in a natural language uttera...

0 Rostislav Nedelchev, et al. ∙

research

∙ 07/22/2019

Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs

Question answering has emerged as an intuitive way of querying structure...

0 Nilesh Chakraborty, et al. ∙

research

∙ 02/04/2019

Predictive Uncertainty Quantification with Compound Density Networks

Despite the huge success of deep neural networks (NNs), finding good mec...

0 Agustinus Kristiadi, et al. ∙

research

∙ 11/13/2018

Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters

Translating natural language to SQL queries for table-based question ans...

0 Denis Lukovnikov, et al. ∙

research

∙ 11/02/2018

Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphs

In this paper, we conduct an empirical investigation of neural query gra...

0 Gaurav Maheshwari, et al. ∙

research

∙ 09/10/2018

Improving Response Selection in Multi-turn Dialogue Systems

Building systems that can communicate with humans is a core problem in A...

0 Debanjan Chaudhuri, et al. ∙

research

∙ 07/13/2018

DNN's Sharpest Directions Along the SGD Trajectory

Recent work has identified that using a high learning rate or a small ba...

4 Stanisław Jastrzębski, et al. ∙

research

∙ 02/03/2018

Incorporating Literals into Knowledge Graph Embeddings

Knowledge graphs, on top of entities and their relationships, contain an...

0 Agustinus Kristiadi, et al. ∙

research

∙ 11/13/2017

Three Factors Influencing Minima in SGD

We study the properties of the endpoint of stochastic gradient descent (...

0 Stanisław Jastrzębski, et al. ∙

research

∙ 09/26/2017

On the regularization of Wasserstein GANs

Since their invention, generative adversarial networks (GANs) have becom...

0 Henning Petzka, et al. ∙

research

∙ 06/16/2017

A Closer Look at Memorization in Deep Networks

We examine the role of memorization in deep learning, drawing connection...

0 Devansh Arpit, et al. ∙

research

∙ 10/09/2015

Early Inference in Energy-Based Models Approximates Back-Propagation

We show that Langevin MCMC inference in an energy-based model with laten...

0 Yoshua Bengio, et al. ∙

research

∙ 10/06/2015

Population-Contrastive-Divergence: Does Consistency help with RBM training?

Estimating the log-likelihood gradient with respect to the parameters of...

0 Oswin Krause, et al. ∙

research

∙ 09/19/2015

STDP as presynaptic activity times rate of change of postsynaptic activity

We introduce a weight update formula that is expressed only in terms of ...

0 Yoshua Bengio, et al. ∙

research

∙ 06/12/2015

Bidirectional Helmholtz Machines

Efficient unsupervised training and inference in deep generative models ...

0 Jörg Bornschein, et al. ∙

research

∙ 12/23/2014

Difference Target Propagation

Back-propagation has been the workhorse of recent successes of deep lear...

0 Dong-Hyun Lee, et al. ∙

Asja Fischer

Featured Co-authors