The idea of this seminar is to make the students familiar with basic algorithms in the field of artificial intelligence (AI). We will not cover neural networks, machine learning or deep learning as this is beyond the scope of this seminar. Alongside with basic AI we also want to introduce explainability. Explainable AI (XAI) is gaining more and more importance in recent years as AI systems take over in various fields. Two prominent examples are self-driving cars and medical disgnosis. Both require lots of confidence in AI and therefore it is of huge importance to be able to understand and comprehend decisions made by AI systems.
Other than in normal proseminars, you will get practical experience with the algorithms and implementations. You will implement one of the XAI algorithms for an AI algorithm (based on the sklearn pipeline) and present both together with the results in a 20 minutes presentation. Additionally, you will write a 5-pages report about you r findings.
Despite the seminar officially is called "Explainability in AI for Drug Discovery" we will not discuss papers applying explanability techniques to AI models used to aid drug discovery. But we will dive deep into these explainability techniques to discuss and understand them. A good overview for XAI in drug discovery and this seminar is provided in Jiménez-Luna et al., published in Nature.
The following requirements are not strictly enforcedbut will make your life way easier in the seminar.
Basic knowledge in
We will check every submission for plagiarism with TurnItIn. This is an online tool automatically checking submissions for plagiarism. You are free (and encouraged) to use it before submitting your final report. Following the link above, you can login with your UdS-credentials (as you use for the students email) and use TurnItIn for free. With attendance of this seminar, you agree that we upload your report to TurnItIn.
If we detect plagiarism in your work, you will have the chance to explain yourself. Ultimately, you will fail this seminar if your explanation is not convincing.
Please register to this seminar by writing an email to Roman Joeres before 30.04.2023 23:59 . Please also attach your transcript of records which can be downloaded from the LSF/HISPOS. The seminar has a limited number of slots. After registration deadline, we will inform you about your participation.
We decided to introduce a partially voluntary milestone system to aid the students if they want to.
All deadlines in this milestone section are until 23:59 MESZ (GMT+2).
You are allowed to implement changes based on the feedback after the "second version of slides"-milestone.
Please send me the final version of your presentation by September 22nd.
All notebooks will deal with the Breast Cancer Dataset from the sklearn package to compare the algorithms performance and have interpretable features and comparable features. We will mainly rely on the sklearn python library.
Topics 1. and 2. will explained based on their implicitly computed feature importance.
Topics 3. and 4. apply their XAI technique to a linear regression model.
From topic 5 on, you will explain a neural network as true black box.
Additional reading, papers that help understanding the bigger picture.
This site was created with the Nicepage