The CNTM extends NTM to model conditional transition graphs and reproduces paths with accuracies from 82.12% on 10-node graphs to 65.25% on 100-node graphs.
Boltzcons: Dynamic symbol structures in a connec- tionist network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Neural Turing~Machine for Conditional Transition Graph Modeling
The CNTM extends NTM to model conditional transition graphs and reproduces paths with accuracies from 82.12% on 10-node graphs to 65.25% on 100-node graphs.