An EM approach to grammatical inference: input/output HMMs

P Frasconi, Y Bengio - … Vol. 3-Conference C: Signal Processing …, 1994 - ieeexplore.ieee.org
Proceedings of the 12th IAPR International Conference on Pattern …, 1994ieeexplore.ieee.org
Proposes a modular recurrent connectionist architecture for adaptive temporal processing.
The model is given, a probabilistic interpretation and is trained using the estimation-
maximisation (EM) algorithm. This model can also be seen as an input/output hidden
Markov model. The focus of this paper is on sequence classification tasks. The authors
demonstrate that EM supervised learning is well suited for solving grammatical inference
problems. Experimental benchmark results are presented for the seven Tomita grammars …
Proposes a modular recurrent connectionist architecture for adaptive temporal processing. The model is given, a probabilistic interpretation and is trained using the estimation-maximisation (EM) algorithm. This model can also be seen as an input/output hidden Markov model. The focus of this paper is on sequence classification tasks. The authors demonstrate that EM supervised learning is well suited for solving grammatical inference problems. Experimental benchmark results are presented for the seven Tomita grammars, showing that these adaptive models can, attain excellent generalization.
ieeexplore.ieee.org
Showing the best result for this search. See all results