2 papers
cs.LG2026
Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints
Patrick Inoue, Florian Röhrbein, Andreas Knoblauch
Introduction: Biological systems face anatomical and metabolic constraints, including costly synaptic maintenance and limited connectivity. These constraints favor neural codes tha…
cs.LG2026
Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations
Patrick Inoue, Florian Röhrbein, Andreas Knoblauch
While deep neural networks (DNNs) have achieved remarkable performance in tasks such as image recognition, they often struggle with generalization, learning from few examples, and…