
On the Pareto Front of PhysicsInformed Neural Networks
Recently a new type of deep learning method has emerged, called physics...
read it

Importance of feature engineering and database selection in a machine learning model: A case study on carbon crystal structures
Drive towards improved performance of machine learning models has led to...
read it

Synwalk – Community Detection via Random Walk Modelling
Complex systems, abstractly represented as networks, are ubiquitous in e...
read it

A Formally Robust Time Series Distance Metric
Distancebased classification is among the most competitive classificati...
read it

On Functions of Markov Random Fields
We derive two sufficient conditions for a function of a Markov random fi...
read it

On Information Plane Analyses of Neural Network Classifiers – A Review
We review the current literature concerned with information plane analys...
read it

SeGMA: SemiSupervised Gaussian Mixture AutoEncoder
We propose a semisupervised generative model, SeGMA, which learns a joi...
read it

ClassConditional Compression and Disentanglement: Bridging the Gap between Neural Networks and Naive Bayes Classifiers
In this draft, which reports on work in progress, we 1) adapt the inform...
read it

A Short Note on the JensenShannon Divergence between Simple Mixture Distributions
This short note presents results about the symmetric JensenShannon dive...
read it

Understanding Individual Neuron Importance Using Information Theory
In this work, we characterize the outputs of individual neurons in a tra...
read it

How (Not) To Train Your Neural Network Using the Information Bottleneck Principle
In this theory paper, we investigate training deep neural networks (DNNs...
read it

CoClustering via InformationTheoretic Markov Aggregation
We present an informationtheoretic cost function for coclustering, i.e...
read it

On the Information Dimension of Multivariate Gaussian Processes
The authors have recently defined the Rényi information dimension rate d...
read it

Semisupervised crossentropy clustering with information bottleneck constraint
In this paper, we propose a semisupervised clustering method, CECIB, t...
read it
Bernhard C. Geiger
is this you? claim profile