Michael Biehl

Latest

• Layered Neural Networks with GELU Activation, a Statistical Mechanics Analysis
• Off-line Learning Analysis for Soft Committee Machines with GELU Activation
• Supervised Learning in the Presence of Concept Drift: A modelling framework
• Hidden Unit Specialization in Layered Neural Networks: ReLU vs. Sigmoidal Activation
• Complex-valued embeddings of generic proximity data
• On-line learning dynamics of ReLU neural networks using statistical physics techniques
• Learning Vector Quantization and relevances in complex coefficient space
• Statistical Mechanics of On-Line Learning Under Concept Drift
• Prototypes and matrix relevance learning in complex Fourier space