Neural networks exhibit condensation of neurons into clusters with similar outputs whose number increases monotonically during training, facilitated by small initializations or dropout, providing insights into generalization and reasoning.
Multi-scale deep neural network (mscalednn) for solving poisson-boltzmann equation in complex domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An overview of condensation phenomenon in deep learning
Neural networks exhibit condensation of neurons into clusters with similar outputs whose number increases monotonically during training, facilitated by small initializations or dropout, providing insights into generalization and reasoning.