WTA bottlenecks enforce highly symbolic, disentangled categorical representations of latent factors under defined conditions in multi-task DNNs, shown via theorem and experiments on two datasets.
Distributed bayesian computation and self-organized learning in sheets of spiking neurons with local lateral inhibition.PloS one, 10(8):e0134356, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
WTA bottlenecks enforce highly symbolic, disentangled categorical representations of latent factors under defined conditions in multi-task DNNs, shown via theorem and experiments on two datasets.