An invertible scalar map is defined as the integral of a positive-output neural network and stacked into an autoregressive normalizing flow (UMNN-MAF) with competitive density-estimation results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unconstrained Monotonic Neural Networks
An invertible scalar map is defined as the integral of a positive-output neural network and stacked into an autoregressive normalizing flow (UMNN-MAF) with competitive density-estimation results.