This is a list of projects past and current that I have worked on. In no particular order. Some of these can be found on my GitHub, some are private, meaning they are not publicly accessible (right now).

  • AnyCount [Private]

    A project in which the main task is to count and characterize many cells in microscopy slides.

  • Turtle [Private]

    A project in which the main task revolves around generating high quality SQL for use in an OMOP CDM based EHR system.

  • Multivariate Time-Series Outlier Detection [Private]

    A project in which we try to find outbreaks / anomalies in multivariate time-series with a training-free algorithm, based around diffusion.

  • GNN Based Regional Covid Forecasting [Private]

    A project in which we try to analyze and forecast the spread of the pandemic in germany by integrating many different data modalities.

  • Improving Traffic Delay Prediction through integration of Weather Effects [Private]

    A project in which we deal with billions of datapoints in a PostGIS database, both location specific as well as raster data. The goal being to improve the forecasting of delays in the traffic flow for logistics.

  • UFLT - Ultra Fast Labeling Tool

    A project trying to deliver a simple to setup and simple to use tool to label many images quickly. Based around PassiveAgressive Classifiers and an interesting representation.

  • SonificationPlayground

    A project I did in my Masters, to explore the capabilities of the WebAudioAPI. Supposed to be used to 3D sonify interesting datasets.

Julia packages I am working on:

  • HiPPO.jl

    Julia implementation of the methods described in Gu et al. “Hippo: Recurrent Memory with Optimal Polynomial Projections”1

  • PureFFT.jl

    A pure Julia implementation of the Cooley-Tukey FFT Algorithm.

  • PassiveAgressive.jl

    OnlineStats.jl compatible Implementation of the methods described in Crammer et al. “Online Passive-Aggressive Algorithms”2

  • BYOL.jl

    Implementation of the “Bootstrap your own Latent” method for Julia.

  1. Gu, A., Dao, T., Ermon, S., Rudra, A., & Ré, C. (2020). Hippo: Recurrent memory with optimal polynomial projections. Advances in neural information processing systems, 33, 1474-1487. ↩︎

  2. K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz, and Y. Singer, “Online Passive-Aggressive Algorithms,” Journal of Machine Learning Research, vol. 7, no. 19, pp. 551–585, 2006. ↩︎