A new era in machine learning


PI Probaligence GmbH


Design of Experiments

STOCHOS can significant improve your Design of Experiments (DOE) by enhancing the efficiency, effectiveness, and insight generation during the experimental process. 
By leveraging STOCHOS techniques in DOE, researchers can streamline the experimentation process, gain deeper insights into complex systems, and make more informed decisions with limited resources.
We have extensive experience, particularly in coatings and similar chemical applications.


Utilizing Gaussian processes (GP),
we pinpoint the most likely function for accurate modeling and predictions


To determine our next training point, we only look on regions with elevated uncertainties to maximize the information gain.

Utilizing our proprietary algorithms, we excel in efficiently identifying correlations between input and output parameters. Our cutting-edge algorithms are specifically designed to navigate through complex datasets, ensuring that we uncover meaningful relationships with precision and effectiveness.

A New Era in Machine Learning

Deep Infinite Mixture of Gaussian Processes: DIM-GP

We accommodate nearly all input types, including scalars, signals, fields, tensors, images, meshes, and more. Our system is designed to seamlessly handle diverse data formats, ensuring versatility and compatibility across various input sources.
We offer the flexibility of choosing from a diverse range of highly specialized covariance functions tailored to meet specific requirements. However, it’s worth noting that our standard setup is generally sufficient for most scenarios, providing a reliable and effective foundation for various applications.
Embedded within our machine learning model is an advanced feature for automatic noise level estimation and outlier avoidance. This innovative capability not only ensures the robustness of our model but also enhances the reliability of data by effectively identifying and mitigating outliers. This sophisticated mechanism contributes to the overall accuracy and stability of our predictions, making our model well-equipped to handle diverse and challenging datasets.

Unique algorithm DIM-GP

What makes us special

ANNs offer scalability, batch learning, and excel in state-of-the-art solutions for tasks like picture classification or time series analysis. On the other hand, GPs require only a minimal amount of input data, involve little to no hyperparameters, allow for model uncertainty calculation, and are proficient at noise detection.

DIM-GP redefines the boundaries of what is achievable. Whether tackling complex classification challenges or navigating intricate time series analyses, this algorithm’s unique fusion of ANNs and Gaussian processes sets new standards in the realm of machine learning.



Social Networks

PI Probaligence GmbH

(c) 2023 All Rights Reserved