
MixMOOD: A systematic approach to class distribution mismatch in semisupervised learning using deep dataset dissimilarity measures
In this work, we propose MixMOOD  a systematic approach to mitigate eff...
read it

Sensor Artificial Intelligence and its Application to Space Systems – A White Paper
Information and communication technologies have accompanied our everyday...
read it

Deep Learning for ECG Analysis: Benchmarks and Insights from PTBXL
Electrocardiography is a very common, noninvasive diagnostic procedure ...
read it

Risk Estimation of SARSCoV2 Transmission from Bluetooth Low Energy Measurements
Digital contact tracing approaches based on Bluetooth low energy (BLE) h...
read it

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution
Integrated gradients as an attribution method for deep neural network mo...
read it

Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training
Deep Neural Networks are successful but highly computationally expensive...
read it

Learning Sparse Ternary Neural Networks with EntropyConstrained Trained Ternarization (EC2T)
Deep neural networks (DNN) have shown remarkable success in a variety of...
read it

Interval Neural Networks as Instability Detectors for Image Reconstructions
This work investigates the detection of instabilities that may occur whe...
read it

Interval Neural Networks: Uncertainty Scores
We propose a fast, nonBayesian method for producing uncertainty scores ...
read it

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond
With the broader and highly successful usage of machine learning in indu...
read it

Towards Ground Truth Evaluation of Visual Explanations
Several methods have been proposed to explain the decisions of neural ne...
read it

Trends and Advancements in Deep Neural Network Communication
Due to their great performance and scalability properties neural network...
read it

Understanding Image Captioning Models beyond Visualizing Attention
This paper explains predictions of image captioning models with attentio...
read it

Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet unHans'ed
Today's machine learning models for computer vision are typically traine...
read it

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
The success of convolutional neural networks (CNNs) in various applicati...
read it

On the Understanding and Interpretation of Machine Learning Predictions in Clinical Gait Analysis Using Explainable Artificial Intelligence
Systems incorporating Artificial Intelligence (AI) and machine learning ...
read it

Asymptotically Unbiased Generative Neural Sampling
We propose a general framework for the estimation of observables with ge...
read it

Towards best practice in explaining neural network decisions with LRP
Within the last decade, neural network based predictors have demonstrate...
read it

Clustered Federated Learning: ModelAgnostic Distributed MultiTask Optimization under Privacy Constraints
Federated Learning (FL) is currently the most widely adopted framework f...
read it

Towards Explainable Artificial Intelligence
In recent years, machine learning (ML) has become a key enabling technol...
read it

Explaining and Interpreting LSTMs
While neural networks have acted as a strong unifying force in the desig...
read it

Resolving challenges in deep learningbased analyses of histopathological images using explanation methods
Deep learning has recently gained popularity in digital pathology due to...
read it

DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
The field of video compression has developed some of the most sophistica...
read it

Deep Transfer Learning For WholeBrain fMRI Analyses
The application of deep learning (DL) models to the decoding of cognitiv...
read it

From Clustering to Cluster Explanations via Neural Networks
A wealth of algorithms have been developed to extract natural cluster st...
read it

Achieving Generalizable Robustness of Deep Neural Networks by Stability Training
We study the recently introduced stability training as a generalpurpose...
read it

DeepCABAC: Contextadaptive binary arithmetic coding for deep neural network compression
We present DeepCABAC, a novel contextadaptive binary arithmetic coder f...
read it

Evaluating Recurrent Neural Network Explanations
Over the last years machine learning (ML) has become a key enabling tech...
read it

BlackBox Decision based Adversarial Attack with Symmetric αstable Distribution
Developing techniques for adversarial attack and defense is an important...
read it

Comment on "Solving Statistical Mechanics Using VANs": Introducing saVANt  VANs Enhanced by Importance and MCMC Sampling
In this comment on "Solving Statistical Mechanics Using Variational Auto...
read it

Robust and CommunicationEfficient Federated Learning from NonIID Data
Federated Learning allows multiple parties to jointly train a deep learn...
read it

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
Current learning machines have successfully solved hard application prob...
read it

MultiKernel Prediction Networks for Denoising of Burst Images
In low light or shortexposure photography the image is often corrupted ...
read it

EntropyConstrained Training of Deep Neural Networks
We propose a general framework for neural network compression that is mo...
read it

Interpretable LSTMs For WholeBrain Neuroimaging Analyses
The analysis of neuroimaging data poses several strong challenges, in pa...
read it

What is Unique in Individual Gait Patterns? Understanding and Interpreting Deep Learning in Gait Analysis
Machine learning (ML) techniques such as (deep) artificial neural networ...
read it

iNNvestigate neural networks!
In recent years, deep neural networks have revolutionized many applicati...
read it

Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
We investigate Early Hybrid Automatic Repeat reQuest (EHARQ) feedback s...
read it

Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals
Interpretability of deep neural networks is a recently emerging area of ...
read it

Understanding PatchBased Learning by Explaining Predictions
Deep networks are able to learn highly predictive models of video data. ...
read it

Accurate and Robust Neural Networks for Security Related Applications Exampled by Face Morphing Attacks
Artificial neural networks tend to learn only what they need for a task....
read it

Counterstrike: Defending Deep Learning Architectures Against Adversarial Samples by Langevin Dynamics with Supervised Denoising Autoencoder
Adversarial attacks on deep learning models have been demonstrated to be...
read it

Compact and Computationally Efficient Representation of Deep Neural Networks
Dot product operations between matrices are at the heart of almost any f...
read it

Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication
Currently, progressively larger deep neural networks are trained on ever...
read it

A Recurrent Convolutional Neural Network Approach for Sensorless Force Estimation in Robotic Surgery
Providing force feedback as relevant information in current RobotAssist...
read it

Dual Recurrent Attention Units for Visual Question Answering
We propose an architecture for VQA which utilizes recurrent layers to ge...
read it

The Convergence of Machine Learning and Communications
The areas of machine learning and communication technology are convergin...
read it

Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
With the availability of large databases and recent improvements in deep...
read it

Understanding and Comparing Deep Neural Networks for Age and Gender Classification
Recently, deep neural networks have demonstrated excellent performances ...
read it

Discovering topics in text datasets by visualizing relevant words
When dealing with large collections of documents, it is imperative to qu...
read it
Wojciech Samek
is this you? claim profile
Head of Machine Learning Group at Fraunhofer Heinrich Hertz Institute HHI