Features

Ease of Use

PHOTON offers an intuitive approach to designing complex machine learning pipelines from scratch in under 3 minutes. Be productive right from the start using e.g. our preloaded sklearn pipelines or Deep Learning model architectures.
Speed

While modern machine learning enables mind-blowing applications, a vast, ever increasing hyperparameter space needs to be searched to optimize machine learning pipelines. PHOTON meets this challenge in two ways:

PHOTON enables intelligent, nested hyperparameter search minimizing the number of function evaluations necessary.

It also allows you to define your own performance expectations in order to rapidly decide if a given configuration is promising or not, not wasting time testing bad configurations.
Expandability

Machine Learning is moving at a neck-breaking pace today. As exciting new algorithms and architectures appear almost every week, we explicitly built PHOTON in a way that allows you to easily integrate with the software you are already using.

PHOTON is designed for cross plattform support, allowing you to take full advantage of all your favorite machine learning packages simultaneously.
Add your favorite elements from any other software package such as preprocessing steps, metrics, and machines using PHOTON’s simple, standardized register.

Also hook up your own neural network models, preprocessing steps or even completely new hyperparameter optimizers using our sklearn-based wrapper interface.

Everything you add is immediately accessible in all your models.
Simplicity

While terrific machine learning tools exist, they focus on the models themselves, mostly neglecting the workflow necessary for rapid prototyping. PHOTON was consequently designed for rapid prototyping, allowing you to build, train and evaluate complete machine learning analyses fast.

PHOTON Modules

PHOTON Modules are add-ons to the PHOTON package which allow users to include modality-specific operations directly into their machine learning pipeline. Thus, users can harness PHOTON's full power while directly working with their favorite modality-specific software or algorithms. In this way, all preprocessing steps can also be used with hyperparameter search.

PHOTON Wizard

The PHOTON Wizard enables you to design complex machine learning pipelines in PHOTON without the need to code.

Ramona Leenings, Nils Winter

AI and Machine Learning in Psychiatry Group

University of Muenster

PHOTON Genetics

PHOTON-Genetics enables loading and preprocessing of genetic data based on the PLINK package.

Prof. Dr. B. Müller-Myhsok

Statistical Genetics

Max Planck Institute of Psychiatry Munich

PHOTON Neuro

PHOTON-Neuro enables loading and proprecessing neuroimaging data such as structural and functional Magnetic Resonance Imaging (MRI) data. In addition, it supports a range of advanced feature extraction and feature engineering as well as atlas-based analyses.

Prof. Dr. Dr. U. Dannlowski

Translational Psychiatry Group

University of Muenster

PHOTON Now

PHOTON-Now enables loading and proprecessing temporal (i.e. time-series) data with a focus on neuroimaging modalities (such as EEG, MEG and resting-state functional MRI) and smartphone sensor data. In addition, it supports a range of advanced time-series analysis tools based on Deep Learning (e.g. LSTMs) and Complex Systems Analysis (e.g. stochastic differential equation modeling).

PD Dr. T. Hahn & Dr. O. Kamps

AI and Machine Learning in Psychiatry Group, Center for Nonlinear Science

University of Muenster

PHOTON Repository

PHOTON-Repository is a platform enabling direct sharing of pre-trained machine learning models - PHOTON-based or otherwise - with the community. It thus allows researchers to disseminate their accomplishments while simultaneously providing a hub for all reseachers seeking state-of-the-art models. Thereby, PHOTON-Repository fosters and supports current efforts towards replicability and real-life validation.

PHOTON Team

AI and Machine Learning in Psychiatry Group

University of Muenster

PHOTON eDoc

PHOTON-eDoc is a growing set of tools and algorithms enabling the analysis of real-life clinical data including for example psychometric data and text from eletronic patient records. It is designed specifically for unstructured data which would otherwise be difficult to handle in machine learning analyses.

Dr. med. Nils Opel, PD Dr. T. Hahn

Translational Psychiatry Group & AI and Machine Learning in Psychiatry Group

University of Muenster