BLBoris Lorbeer

Boris Lorbeer

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Boris Lorbeer has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Anomaly Detection With Partitioning Overfitting Autoencoder Ensembles

    by Boris Lorbeer, Max Botler

    In this paper, we propose POTATOES (Partitioning OverfiTting AuTOencoder EnSemble), a new method for unsupervised outlier detection (UOD). More precisely, given any autoencoder for UOD, this technique can be used to improve its accuracy while at the same time removing the burden of tuning its regularization. The idea is to not regularize at all, but to rather randomly partition the data into sufficiently many equally sized parts, overfit each part with its own autoencoder, and to use the maximum over all autoencoder reconstruction errors as the anomaly score. We apply our model to various realistic datasets and show that if the set of inliers is dense enough, our method indeed improves the UOD performance of a given autoencoder significantly. For reproducibility, the code is made available on github so the reader can recreate the results in this paper as well as apply the method to other autoencoders and datasets.

  • Open Access

    Anomaly Detection with HMM Gauge Likelihood Analysis

    by Boris Lorbeer, Tanja Deutsch, Peter Ruppel, Axel Küpper

    This paper describes a new method, HMM gauge likelihood analysis, or GLA, of detecting anomalies in discrete time series using Hidden Markov Models and clustering. At the center of the method lies the comparison of subsequences. To achieve this, they first get assigned to their Hidden Markov Models using the Baum-Welch algorithm. Next, those models are described by an approximating representation of the probability distributions they define. Finally, this representation is then analyzed with the help of some clustering technique or other outlier detection tool and anomalies are detected. Clearly, HMMs could be substituted by some other appropriate model, e.g. some other dynamic Bayesian network. Our learning algorithm is unsupervised, so it does not require the labeling of large amounts of data. The usability of this method is demonstrated by applying it to synthetic and real-world syslog data.

  • A-BIRCH: Automatic Threshold Estimation for the BIRCH Clustering Algorithm

    by Boris Lorbeer, Ana Kosareva, Bersant Deva, Dženan Softić, Peter Ruppel, Axel Küpper