
Fitted QLearning for Relational Domains
We consider the problem of Approximate Dynamic Programming in relational...
read it

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Probabilistic circuits (PCs) are a promising avenue for probabilistic mo...
read it

CryptoSPN: Privacypreserving SumProduct Network Inference
AI algorithms, and machine learning (ML) techniques in particular, are i...
read it

Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations
Deep neural networks have shown excellent performances in many realworl...
read it

BERT has a Moral Compass: Improvements of ethical and moral values of machines
Allowing machines to choose whether to kill humans would be devastating ...
read it

Structured ObjectAware Physics Prediction for Video Modeling and Planning
When humans observe a physical system, they can easily locate objects, u...
read it

DeepDB: Learn from Data, not from Queries!
The typical approach for learned DBMS components is to capture the behav...
read it

Neural Networks for Relational Data
While deep networks have been enormously successful over the last decade...
read it

Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
Deep neural networks have been successfully applied in learning the boar...
read it

Random SumProduct Forests with Residual Links
Tractable yet expressive density estimators are a key building block of ...
read it

Padé Activation Units: Endtoend Learning of Flexible Activation Functions in Deep Networks
The performance of deep network learning strongly depends on the choice ...
read it

Declarative LearningBased Programming as an Interface to AI Systems
Datadriven approaches are becoming more common as problemsolving techn...
read it

NeuralSymbolic Argumentation Mining: an Argument in Favour of Deep Learning and Reasoning
Deep learning is bringing remarkable contributions to the field of argum...
read it

Conditional SumProduct Networks: Imposing Structure on Deep Probabilistic Architectures
Bayesian networks are a central tool in machine learning and artificial ...
read it

Was ist eine Professur fuer Kuenstliche Intelligenz?
The Federal Government of Germany aims to boost the research in the fiel...
read it

SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using SumProduct Networks
We introduce SPFlow, an opensource Python library providing a simple in...
read it

Modelbased Approximate Query Processing
Interactive visualizations are arguably the most important tool to explo...
read it

Structure Learning for Relational Logistic Regression: An Ensemble Approach
We consider the problem of learning Relational Logistic Regression (RLR)...
read it

Automatic Bayesian Density Analysis
Making sense of a dataset in an automatic and unsupervised fashion is a ...
read it

Probabilistic Deep Learning using Random SumProduct Networks
Probabilistic deep learning currently receives an increased interest, as...
read it

"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users
Although interactive learning puts the user into the loop, the learner r...
read it

Neural Conditional Gradients
The move from handdesigned to learned optimizers in machine learning ha...
read it

Lifted Filtering via Exchangeable Decomposition
We present a model for recursive Bayesian filtering based on lifted mult...
read it

SumProduct Networks for Hybrid Domains
While all kinds of mixed data from personal data, over panel and scient...
read it

Coresets for Dependency Networks
Many applications infer the structure of a probabilistic graphical model...
read it

Global WeisfeilerLehman Graph Kernels
Most stateoftheart graph kernels only take local graph properties int...
read it

A Unifying View of Explicit and Implicit Feature Maps for Structured Data: Systematic Studies of Graph Kernels
Nonlinear kernel methods can be approximated by fast linear ones using ...
read it

Faster Kernels for Graphs with Continuous Attributes via Hashing
While stateoftheart kernels for graphs with discrete labels scale wel...
read it

Machine Learning meets DataDriven Journalism: Boosting International Understanding and Transparency in News Coverage
Migration crisis, climate change or tax havens: Global challenges need g...
read it

Lifted Convex Quadratic Programming
Symmetry is the essential element of lifted inference that has recently ...
read it

How is a datadriven approach better than random choice in label space division for multilabel classification?
We propose using five datadriven community detection approaches from so...
read it

The Symbolic Interior Point Method
A recent trend in probabilistic inference emphasizes the codification of...
read it

Propagation Kernels
We introduce propagation kernels, a general graphkernel framework for e...
read it

Relational Linear Programs
We propose relational linear programming, a simple framework for combing...
read it

Mind the Nuisance: Gaussian Process Classification using Privileged Noise
The learning with privileged information setting has recently attracted ...
read it

Efficient Information Theoretic Clustering on Discrete Lattices
We consider the problem of clustering data that reside on discrete, low ...
read it

Latent Dirichlet Allocation Uncovers Spectral Characteristics of Drought Stressed Plants
Understanding the adaptation process of plants to drought stress is esse...
read it

'Say EM' for Selecting Probabilistic Models for Logical Sequences
Many real world sequences such as protein secondary structures or shell ...
read it

Counting Belief Propagation
A major benefit of graphical models is that most knowledge is captured i...
read it
Kristian Kersting
is this you? claim profile
Professor in Computer Science Department and Centre for Cognitive Science at TU Darmstadt