Softwareproject: Machine Learning and Explainability for Improved (Cancer) Treatment

In the software project, we will implement, train, and evaluate various machine learning (ML) methods. The focus of the project is on neural networks (NN) and their explainability. We will compare the methods with different baseline models, such as regression models. The various ML methods will be applied to a specific dataset, e.g., for predicting drug combinations for cancer treatment, and evaluated accordingly. The dataset will be prepared by us and analyzed using the implemented methods. Additionally, we will focus on explainability to ensure that the predictions of the ML models are understandable and interpretable. For this purpose, we will integrate appropriate explainability techniques to better understand and visualize the decision-making processes of the models.

The programming language is Python, and we plan to use modern Python modules for ML like scikit-learn, and PyTorch. Good Python skills are required. The goal is to create a Python package that provides reusable code for preprocessing, training ML models, and evaluating results with documentation (e.g., using Sphinx) for the specific use case. The software project takes place throughout the semester and can also be conducted in English.

___

Weekly seminar

Tuesdays 15:30 (3:30pm) in room T9/K40 (down stairs) 

Online: https://fu-berlin.webex.com/fu-berlin/j.php?MTID=m90ea095a1ae820a4b3a7552fafcfd127 
If you participate online please turn on your video, otherwise it will not count towards the active and regular participation. Also always let me know beforehand if you want to participate online so that I can start the Webex meeting