mkirchhof
Statistician who plays around with probabilistic machine learning. Currently a Ph.D. student at Prof. E. Kasneci and Seong Joon Oh at the University of Tübingen
University of TübingenGermany
Pinned Repositories
Annotation_Tool_LARa
Annotation Tool LARa Dataset
AnotherRSS
The App AnotherRSS is a free Atom RSS Feed Reader and very similar to ViboraFeed.
dominantAdmixtureModel
Implementation of the Dominant Admixture Model for Topic Modeling, as proposed by Blum et. al. in "Foundations of Data Science".
interpretable-ml-book
Book about interpretable machine learning
LAGO
Code for our paper: Atzmon & Chechik, "Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning", UAI 2018
NotifyFitness
R functions to import the fitness tracker data from a backup created by the Android app "Notify & Fitness".
Probabilistic_Contrastive_Learning
This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs".
pytorch_influence_functions_stable
This is a [Stable] PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
self-adapting-keyboard
Android Keyboard that automatically adapts its layout to minimize mistyping rate of the individual user.
url
Uncertainty-aware representation learning (URL) benchmark
mkirchhof's Repositories
mkirchhof/url
Uncertainty-aware representation learning (URL) benchmark
mkirchhof/Probabilistic_Contrastive_Learning
This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs".
mkirchhof/self-adapting-keyboard
Android Keyboard that automatically adapts its layout to minimize mistyping rate of the individual user.
mkirchhof/pytorch_influence_functions_stable
This is a [Stable] PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
mkirchhof/interpretable-ml-book
Book about interpretable machine learning
mkirchhof/LAGO
Code for our paper: Atzmon & Chechik, "Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning", UAI 2018
mkirchhof/Annotation_Tool_LARa
Annotation Tool LARa Dataset
mkirchhof/AnotherRSS
The App AnotherRSS is a free Atom RSS Feed Reader and very similar to ViboraFeed.
mkirchhof/dominantAdmixtureModel
Implementation of the Dominant Admixture Model for Topic Modeling, as proposed by Blum et. al. in "Foundations of Data Science".
mkirchhof/NotifyFitness
R functions to import the fitness tracker data from a backup created by the Android app "Notify & Fitness".
mkirchhof/optPieces
This algorithm finds the best pieces of a fixed length within a long production line regarding multiple quality measurements. Find the technical report here (http://dx.doi.org/10.17877/DE290R-19935). A peer reviewed paper is on its way.
mkirchhof/optPiecesRuntimeStudy
A runtime study of the specialized knapsack optimizer used in the optPieces algorithm (https://github.com/mkirchhof/optPieces). For further information and results, please have a look at the paper (Accepted for ECDA 2018 proceedings, link will be inserted once published)
mkirchhof/rsl
Rule Stacking Learner for combining multi-label classificators with probabilistic rules in a bayesian network
mkirchhof/rslAppl
Application of pRSL to the logistics human activity recognition transfer learning challenge for the ICCL 2021 paper.
mkirchhof/rslBench
Benchmarks of pRSL on six datasets for multi-label classification for the UAI 2021 paper.
mkirchhof/rslSim
Simulation experiments to test pRSL's approximate inference methods for the UAI 2021 paper.
mkirchhof/scalabletrustworthyai.github.io
mkirchhof/SWATEliteForce_TacTic
A modification for SWAT 4: The Stetchkov Syndicate