An Input Output HMM Architecture
Abstract
We introduce a recurrent architecture having a modular structure and we formulate a training procedure based on the EM algorithm. The resulting model has similarities to hidden Markov models, but supports recurrent networks processing style and allows to exploit the supervised learning paradigm while using maximum likelihood estimation.
Cite
Text
Bengio and Frasconi. "An Input Output HMM Architecture." Neural Information Processing Systems, 1994.Markdown
[Bengio and Frasconi. "An Input Output HMM Architecture." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/bengio1994neurips-input/)BibTeX
@inproceedings{bengio1994neurips-input,
title = {{An Input Output HMM Architecture}},
author = {Bengio, Yoshua and Frasconi, Paolo},
booktitle = {Neural Information Processing Systems},
year = {1994},
pages = {427-434},
url = {https://mlanthology.org/neurips/1994/bengio1994neurips-input/}
}