An Input Output HMM Architecture

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.

• Type: Conference
• Year: 1994
• Where: NIPS
• Authors: Yoshua Bengio, Paolo Frasconi
• Keywords: Hidden Markov Models, NIPS 1994, NIPS 2007, Recurrent Architecture, Supports Recurrent Networks