Master's Theses and Projects at PGI-15

Master's Thesis: Power Law Scaling of Foundational Models using Local Learning

The goal of this Master’s thesis is to explore the power law scaling (Cherti et al. 2023) of neuromorphic algorithms and hardware by replacing conventional global backpropagation with biologically inspired local learning rules.

More

The goal of this Master’s thesis is to explore the power law scaling (Cherti et al. 2023) of neuromorphic algorithms and hardware by replacing conventional global backpropagation with biologically inspired local learning rules.

More
Master’s Theses: Neuromorphic and Neuro-inspired AI

In these projects, we aim to investigate how neuromorphic principles and the entorhinal-hippocampal formation — the brain’s navigation system — can inspire modern machine learning.

More

In these projects, we aim to investigate how neuromorphic principles and the entorhinal-hippocampal formation — the brain’s navigation system — can inspire modern machine learning.

More

Last Modified: 02.02.2025