Overview Diagram

A specialized workshop—the first in this series—was held in the spring of 2023 in Guntersblum. This event was funded by the Begegnungszonen program of the Joachim Herz Foundation and was designed to provide a novel opportunity at the intersection of machine learning and neuroscience. The spirit of the funding program supported the workshop’s central aim: “supporting the design and implementation of interdisciplinary events for young scientists.”

To this end, 16 doctoral students and postdoctoral researchers were brought together to explore relevant and compelling questions in the field of biologically inspired deep learning. Over several days, participants engaged with foundational and emerging ideas, fostering an interdisciplinary environment that encouraged the exchange of perspectives across research areas.

The 2023 workshop focused on the credit assignment problem—one of the central challenges in understanding how learning systems adjust their internal representations in response to feedback. Prof. Ponte Costa from the Department of Computer Science at the University of Bristol served as the lead instructor. He was joined by his doctoral students, Will Greedy and Joseph Pemberton, who contributed tutorials and practical sessions.

This report briefly introduces the motivation and underlying ideas behind the workshop series, highlights the importance of credit assignment in bio-inspired deep learning, and presents representative examples of the students’ work during the event.

You can download the final workshop bulletin here:

📄 Download Workshop Document (PDF)