Geometric Transformations
Max and Tim discuss the impact of inductive bias on neural networks, emphasizing the importance of explicitly defining priors for efficient learning. They delve into the constraints and benefits of axial representations in hidden layers, highlighting how geometric transformations play a crucial role in shaping machine learning models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#036 - Max Welling: Quantum, Manifolds & Symmetries in ML
Related Questions