Ml

Systematization of knowledge in the field of Post-hoc Concept-Based Explanations.

This post is about turning a photo of a cat into a photo of a goldfish by changing only one pixel, at least according to resnet50. With Organizers we participated in RCTF during the close race at the end of 2022 to be #1 on CTFtime. This literally meant participating in every high-rated CTF and solving every challenge, including the miscy of the misc. The challenge catspy appeared at around 2am in the misc category and the description states:

The lecture Machine Learning for the Natural Sciences promises to focus on applications of machine learning to natural sciences, especially physics and chemistry. However, most of the actual content is repeating machine learning basics that are already covered in foundational lectures on machine learning. In the remaining time, a few interesting topics are presented, but sadly just very shallowly.

With KITCTF we participated in the b01lers CTF and finished 6th. There were some quite fun challenges, including the resnet challenge, which is a machine learning challenge. I hope to see more machine learning challenges in the future.

Answers to self-test questions for the lecture “Data Science I” at KIT. If you spot any errors, write me an e-mail or Discord message.

Self-test questions for the lecture “Machine Learning - Foundations and Algorithms” at KIT.

The mind map below summarizes topics from the lecture. I use mind maps like this at the start of exam preparation to see what I remember from the semester. While studying, I expand on the topics. Later, I color-code the nodes to show which topics I know well and which ones I still need to practice.