Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints
Introduction: Biological systems face anatomical and metabolic constraints, including costly synaptic maintenance and limited connectivity. These constraints favor neural codes that compress behaviorally relevant information into low-redundancy patterns. We test whether an excitatory competitive Hebbian rule can support synaptic resource allocation under such constraints and whether the resulting representations occupy a more favorable cost-performance regime than reference learning rules. Methods: Representational cost is quantified using mutual-information-based measures derived from the V
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%A unifying framework from neural superposition to sparse interpretable codes →
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Constrained Hebbian Learning Supports Efficient Representati” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Patrick Inoue →
“Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints”
- LinkedLinked via arxiv author · 85%Florian Röhrbein →
“Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints”
- LinkedLinked via arxiv author · 85%Andreas Knoblauch →
“Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints”