After successful completion of the course, students are able to

• to name relevant aspects about neuroscience-based AI,
• to describe the current research for a chosen topic from the area of neuroscience-based AI, and
• to find relevant literature for a topic from research about neuroscience-based AI.

At the end of the course, the students will be able to read and critique scientific papers. They will be able to analyse the methods proposed in the field of neuroscience-based AI, and evaluate their strengths and weaknesses. They will be able to prepare an oral presentation of their findings and discuss the studied methods in detail. Finally, they will be able to assess their peers’ work.

The seminar will cover topics belonging to a relevant subfield of machine learning and artificial intelligence (AI): neuroscience-inspired AI.

The course will explore the intersection of computational neuroscience and machine learning, examining how they can help advance AI. Computational neuroscience uses mathematical models of the brain to understand the principles that govern neural systems. Combined with machine learning, it enables the development of algorithms that can model neural processing, offering insights into both neuroscience and AI. Typical problems include decoding the computation behind neural activity or deriving learning mechanisms that are biologically plausible. Key areas of focus for this seminar include:

• Biologically plausible learning methods: Explore alternatives to backpropagation like predictive coding, Hebbian learning, and spike-timing-dependent plasticity.
• Bridging the gap between machine learning and neuroscience: Learn about the fundamental differences between artificial neural networks and biological neural networks as well as the similarities.
• Computational models for brain function: Examine models that decode how the brain processes information, stores memories, and makes decisions.

The students have to

• perform a literature research for a selected topic,
• prepare a presentation draft about the chosen topic, and
• give a presentation of 50min.

Students attend the kick-off meeting. In the kick-off meeting, each student is allocated to a topic and a paper. After the kick-off meeting, each student is expected to read the assigned paper and the papers belonging to their topic, and to perform a literature review of the related work. Four weeks after the kick-off meeting, each student is expected to schedule a meeting with their advisor to discuss their findings. In January, there will be a presentation day. During the presentation day, each student is expected to prepare a 15 min presentation where their findings are summarised. After all students covering a particular topic have presented, there will be a 30 min panel discussion. During the panel discussion, each student will advocate for the ideas presented in their paper, and compare and contrast them to the ideas presented by others. After the presentation, the advisor meets their student to give them feedback on their presentation and discuss the structure of the seminar paper. Each student will write a seminar paper (6-7 pages + references) on their topic, where the central ideas and methods presented in the talk are summarised. Each student will also write two reviews (~0.5 pages) of the manuscripts submitted by other fellow students.

Immanent.