The paper frames transformer layers as fixed-point updates on conditional probability surrogates and gives an explicit such update for hidden Markov models.
Linear Estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What can we learn from signals and systems in a transformer? Insights for probabilistic modeling and inference architecture
The paper frames transformer layers as fixed-point updates on conditional probability surrogates and gives an explicit such update for hidden Markov models.