Belief Net learns HMM parameters by implementing the forward filter as a decoder-only neural network whose weights are the logits of the initial, transition, and emission distributions, trained end-to-end with autoregressive loss.
Large-scale machine learning with stochastic gradient descent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Differentiable Filtering for Learning Hidden Markov Models
Belief Net learns HMM parameters by implementing the forward filter as a decoder-only neural network whose weights are the logits of the initial, transition, and emission distributions, trained end-to-end with autoregressive loss.