Interactive, mixed-initiative machine learning promises to combine the efficiency of automation with the effectiveness of humans for a collaborative decision-making and problem-solving process. This can be facilitated through co-adaptive visual interfaces. This course will first introduce the foundations of information visualization design based on data charecteristics, e.g., high-dimensional, geo-spatial, relational, temporal, and textual data. Second, we will discuss interaction techniques and explanation strategies to enable explainable machine learning with the tasks of understanding, diagnosing, and refining machine learning models.
The course will give students an overview of selected topics in advanced machine learning that are currently subjects of active research. The course concludes with a final project. The overall objective is to give students a concrete idea of what working in contemporary machine learning research is like and inform them about current research performed at ETH.
The publication lifecycle is at the heart of scientific work. It starts with generating and managing ideas, via finding related work, to focusing on specific research questions and finally writing a paper. Paper writing itself is a form of storytelling targeting fellow peers and researchers to communicate your findings and inspire new ideas. In this workshop series, we will guide you through this process in five sessions. We encourage you to attend the complete series, and to bring your own rough ideas which you will develop into a concrete plan for a paper over the course of the workshops. In particular, we will discuss how to construct a paper based on all its components, how to form a storyline, and how to create a timeline for your writing. To round off the series, we will dedicate a session on critiquing papers and discuss best-practices for science ethics. We are looking forward to combining active discussions with senior researchers, exchange with your peers and hands-on exercises to structure your next paper.