Software

We believe that a successful application of machine learning requires a strong software engineering foundation. To this end, we develop software to support researchers and practitioners, providing high-level libraries for machine learning, as well as reference implementations of new algorithms. We test and benchmark methods, delivering robust, well-documented and tested code beyond what is usually found in academic papers.

Projects

sbi: the simulation-based inference toolkit

sbi is a Python package for Bayesian parameter inference on simulators. It implements state-of-the-art algorithms and comes with comprehensive documentation and tutorials, making it suitable for SBI practitioners. Additionally, it offers low-level modularity for researchers who wish to explore more advanced aspects of SBI.

Jan Teusen Maternus Herold Faried Abu Zaid
Simulation-Based Inference

optimagic: unifying the numerical optimization ecosystem in Python

optimagic is a Python package for numerical optimization. It is a unified interface to optimizers from SciPy, NlOpt and other packages. optimagic’s minimize function works just like SciPy’s, so you don’t have to adjust your code. You simply get more optimizers for free. On top you get diagnostic tools, parallel numerical derivatives and more.

Janoś Gabler
Optimization in ML

pyDVL: the python Data Valuation Library

pyDVL strives to offer reference implementations of algorithms for data valuation and influence function computation, with an emphasis on robustness, simple parallelization and ease of use.

Anes Benmerzoug Miguel de Benito Delgado Janoś Gabler Fabio Peruzzo Kristof Schröder Markus Semmler
Data Valuation

Tianshou: An elegant deep reinforcement learning library

Tianshou is a deep reinforcement learning library based on pure PyTorch. It caters to the needs of researchers and practitioners alike by offering a mix of low-level interfaces for maximum control and high-level interfaces for ease of use. It supports a wide range of state-of-the-art algorithms, all implementations being optimised for speed.

Michael Panchenko Dominik Jain Maximilian Hüttenrauch
Reinforcement Learning

Past Projects

continuiti: Learning Function Operators with Neural Networks

continuiti is a Python package for machine learning on function operators. It implements various neural operator architectures (e.g., DeepONets), physics-informed loss functions, and a collection of examples and benchmarks.

Samuel Burbulla Jakob Wagner
Simulation and AI

sensAI: The Python Library for Sensible AI

sensAI is a high-level AI toolkit with a specific focus on rapid experimentation for machine learning applications. It provides a unifying interface to a wide variety of model classes, integrating industry-standard machine learning libraries. Based on object-oriented design principles, it fosters modularity and facilitates the creation of composable data processing pipelines. Through its high …

Dominik Jain Michael Panchenko Kristof Schröder

AutoDev: LLM-Based Coding Assistance Functions

AutoDev is a software package for the realisation of coding assistance functions using large language models (LLMs). It covers fine-tuning, inference as well as IDE integration.

Dominik Jain
Large Language Models

kyle - A toolkit for classifier calibration

There exist a number of different methods for calibrating models, and for measuring and visualizing calibration. Given the lack of reliable and maintained libraries, appliedAI is developing and open sourcing the library kyle to fill this gap.

Michael Panchenko Miguel de Benito Delgado
Classifier Calibration

K.A.L.E. - The calibration game

The calibration game simulates resource allocation (medicine) for healthcare. A limited budget constraints prescription to patients with varying types of disease and a given expected life expectancy. The goal of the game is to maximise the total expected lifespan.

Michael Panchenko Miguel de Benito Delgado
Classifier Calibration