scikit-mine : pattern mining in Python

Knowledge Graph summarization for anomaly/error detection & completion (WebConf '20)

Minimum Description Length Recurrent Neural Networks (MDLRNNs) in PyTorch

Minimum Description Length Recurrent Neural Networks

MDL Complexity computations and experiments from the paper "Revisiting complexity and the bias-variance tradeoff".

Code for paper "InfoShield: Generalizable Information-Theoretic Human-Trafficking Detection" (ICDE 2021)

Implementation of the genetic algorithm for structural break detection in time series that chooses a piecewise autoregressive model using minimum description length principle

The provided program jointly optimizes a multilinear face model and the registration of the face scans used for model training.

Python implementation of the K2 algorithm for structural learning of Bayesian Networks.

The provided program robustly learns a multilinear face model from databases with missing data, corrupt data, wrong semantic correspondence, and inaccurate vertex correspondence.

Minimum Description Length Hopfield Networks

Seminar paper (@ Technical University Munich) on parameter free clustering of weighted graphs using PaCCo (Parameter-free Clustering by Coding costs)

The framework for finding multiresolution partitions that have homogeneous linear models from multiresolution dataset.

This repository contains Java and C++ implementations of the algorithm GEMPE introduced in the KDD 2020 paper "Data Compression as a Comprehensive Framework for Graph Drawing and Representation Learning" by Claudia Plant, Sonja Biedermann and Christian Böhm.

Estimating the parametric complexity (minimum description length) of binary classifiers.

Demonstrating how to use crude MDL to regularize polynomial regression models.

Learning Bayesian Networks with the Complete Minimum Description Length

Code of HMG: Heuristic-driven MDL-based Genome sequence compressor