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

Rethinking Assumptions in Deep Anomaly Detection
Though anomaly detection (AD) can be viewed as a classification problem ...
read it

Shearlets as Feature Extractor for Semantic Edge Detection: The ModelBased and DataDriven Realm
Semantic edge detection has recently gained a lot of attention as an ima...
read it

Forecasting Industrial Aging Processes with Machine Learning Methods
By accurately predicting industrial aging processes (IAPs), it is possib...
read it

Deep Anomaly Detection by Residual Adaptation
Deep anomaly detection is a difficult task since, in high dimensions, it...
read it

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
Variational inference has become one of the most widely used methods in ...
read it

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

A Markerless Deep Learningbased 6 Degrees of Freedom PoseEstimation for with Mobile Robots using RGB Data
Augmented Reality has been subject to various integration efforts within...
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

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

Deep SemiSupervised Anomaly Detection
Deep approaches to anomaly detection have recently shown promising resul...
read it

Videobased Bottleneck Detection utilizing Lagrangian Dynamics in Crowded Scenes
Avoiding bottleneck situations in crowds is critical for the safety and ...
read it

A 3DDeepLearningbased Augmented Reality Calibration Method for Robotic Environments using Depth Sensor Data
Augmented Reality and mobile robots are gaining much attention within in...
read it

Autonomous robotic nanofabrication with reinforcement learning
The ability to handle single molecules as effectively as macroscopic bui...
read it

A deep neural network for molecular wave functions in quasiatomic minimal basis representation
The emergence of machine learning methods in quantum chemistry provides ...
read it

Learning The Invisible: A Hybrid Deep LearningShearlet Framework for Limited Angle Computed Tomography
The high complexity of various inverse problems poses a significant chal...
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

Local Bandwidth Estimation via Mixture of Gaussian Processes
Real world data often exhibit inhomogeneity  complexity of the target f...
read it

MultiClass Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation
We propose a new scalable multiclass Gaussian process classification ap...
read it

Between Subjectivity and Imposition: Power Dynamics in Data Annotation for Computer Vision
The interpretation of data is fundamental to machine learning. This pape...
read it

Efficient Bayesian Inference of Sigmoidal Gaussian Cox Processes
We present an approximate Bayesian inference approach for estimating the...
read it

Backprop Evolution
The backpropagation algorithm is the cornerstone of deep learning. Desp...
read it

Anomaly Detection with HMM Gauge Likelihood Analysis
This paper describes a new method, HMM gauge likelihood analysis, or GLA...
read it

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

VRLS: A Unified Reinforcement Learning Scheduler for VehicletoVehicle Communications
Vehicletovehicle (V2V) communications have distinct challenges that ne...
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

Molecular Dynamics with NeuralNetwork Potentials
Molecular dynamics simulations are an important tool for describing the ...
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

Generating equilibrium molecules with deep neural networks
Discovery of atomistic systems with desirable properties is a major chal...
read it

Differential Privacy for Eye Tracking with Temporal Correlations
Head mounted displays bring eye tracking into daily use and this raises ...
read it

Controlling Fairness and Bias in Dynamic LearningtoRank
Rankings are the primary interface through which many online platforms m...
read it

On the minimum FLOPs problem in the sparse Cholesky factorization
Prior to computing the Cholesky factorization of a sparse, symmetric pos...
read it

Computational Complexity Aspects of Point Visibility Graphs
A point visibility graph is a graph induced by a set of points in the pl...
read it

Finding Shortest Paths between Graph Colourings
The kcolouring reconfiguration problem asks whether, for a given graph ...
read it

Stochastic Runtime Analysis of a Cross Entropy Algorithm for Traveling Salesman Problems
This article analyzes the stochastic runtime of a CrossEntropy Algorith...
read it

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

Explaining Predictions of NonLinear Classifiers in NLP
Layerwise relevance propagation (LRP) is a recently proposed technique ...
read it

SchNet: A continuousfilter convolutional neural network for modeling quantum interactions
Deep learning has the potential to revolutionize quantum chemistry as it...
read it

Methods for Interpreting and Understanding Deep Neural Networks
This paper provides an entry point to the problem of interpreting a deep...
read it

Context encoders as a simple but powerful extension of word2vec
With a simple architecture and the ability to learn meaningful word embe...
read it

Learning how to explain neural networks: PatternNet and PatternAttribution
DeConvNet, Guided BackProp, LRP, were invented to better understand deep...
read it

A statistical physics approach to learning curves for the Inverse Ising problem
Using methods of statistical physics, we analyse the error of learning c...
read it

NonDeterministic Policy Improvement Stabilizes Approximated Reinforcement Learning
This paper investigates a type of instability that is linked to the gree...
read it

Changing Views on Curves and Surfaces
Visual events in computer vision are studied from the perspective of alg...
read it

Feature Importance Measure for Nonlinear Learning Algorithms
Complex problems may require sophisticated, nonlinear learning methods ...
read it

Approximate Bayes learning of stochastic differential equations
We introduce a nonparametric approach for estimating drift and diffusion...
read it

Optimal control for a robotic exploration, pickup and delivery problem
This paper addresses an optimal control problem for a robot that has to ...
read it

Signal Recovery from Unlabeled Samples
In this paper, we study the recovery of a signal from a set of noisy lin...
read it

Learning from Label Proportions in BrainComputer Interfaces: Online Unsupervised Learning with Guarantees
Objective: Using traditional approaches, a BrainComputer Interface (BCI...
read it

"What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
Text documents can be described by a number of abstract concepts such as...
read it
Berlin Institute of Technology (Technische Universität Berlin)
Homepage of the Technische Universität Berlin. TU Berlin sees itself as an internationally renowned university in the German capital, in the centre of Europe.