A single shared-weight network that encodes on the forward pass and decodes on the backward pass can halve VAE parameters while keeping performance roughly on par with a standard VAE.
Deeper neural networks with non-vanishing logistic hidden units: Nova vs. relu neurons,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bidirectional Variational Autoencoders
A single shared-weight network that encodes on the forward pass and decodes on the backward pass can halve VAE parameters while keeping performance roughly on par with a standard VAE.