no code implementations • 28 Sep 2020 • Matthew Baucum, Anahita Khojandi, Theodore Papamarkou
To allow for this, we formulate a special case of recurrent neural networks (RNNs), which we name hidden Markov recurrent neural networks (HMRNNs), and prove that each HMRNN has the same likelihood function as a corresponding discrete-observation HMM.