A constrained Hebbian rule produces audiovisual representations with lower task-information cost (retained input information per unit of task-relevant information) than sparse backpropagation and DDTP at comparable accuracy in several settings.
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints
A constrained Hebbian rule produces audiovisual representations with lower task-information cost (retained input information per unit of task-relevant information) than sparse backpropagation and DDTP at comparable accuracy in several settings.