ePoster · Machine Learning
What should a neuron aim for? Designing local objective functions based on information theory
Andreas Schneider, Valentin Neuhaus, David Ehrlich, Alexander Ecker, Abdullah Makkeh, Viola Priesemann, Michael Wibral · Bernstein Conference 2024
In modern deep neural networks, the intricate learning dynamics of individual neurons often remain obscured due to global optimization methods. This contrasts with biological neural networks, which achieve robustness and efficiency through self-organized, local learning processes using limited global information. To bridge this gap, a local learning framework inspired by the self-organizing principles of biological neurons has been proposed [1]. This framework allows for the investigation of how local information-processing goals can drive the emergence of complex network-level functions. The