flâneur — a map of the web's best reading

Deep Markov Model — Pyro Tutorials 1.8.4 documentation

pyro.ai · 8,753 words · saved by 1 readers

We’re going to build a deep probabilistic model for sequential data: the deep markov model. The particular dataset we want to model is composed of snippets of polyphonic music. Each time slice in a sequence spans a quarter note and is represented by an 88-dimensional binary vector that encodes the notes at that time step. Since music is (obviously) temporally coherent, we need a model that can represent complex time dependencies in the observed data. It would not, for example, be appropriate to consider a model in which the notes at a particular time step are independent of the notes at previous time steps. One way to do this is to build a latent variable model in which the variability and temporal structure of the observations is controlled by the dynamics of the latent variables. One particular realization of this idea is a markov model, in which we have a chain of latent variables, with each latent variable in the chain conditioned on the previous latent variable. This is a powerful

Deep Markov Model - Pyro Tutorials 1.9.1 documentation >> Deep Markov Model View page source Deep Markov Model ¶ Introduction ¶ We’re going to build a deep probabilistic model for sequential data: the deep markov model. The particular dataset we want to model is composed of snippets of polyphonic music. Each time slice in a sequence spans a quarter note and is represented by an 88-dimensional binary vector that encodes the notes at that time step. Since music is (obviously) temporally coherent, we need a model that can represent complex time dependencies in the observed data. It would not, for

Explore this link on the map →

saved by

related reading