pyjuice.structures.HMM

pyjuice.structures.HMM(seq_length: int, num_latents: int, num_emits: int, homogeneous: bool = True, block_size: int | None = None, alpha: Tensor | None = None, beta: Tensor | None = None, gamma: Tensor | None = None)

Constructs Hidden Markov Models.

Parameters:

• seq_length (int) – sequence length

• num_latents (int) – size of the latent space

• num_emits (int) – size of the emission space

• homogeneous (bool) – whether to define a homogeneous (or inhomogeneous) HMM

• block_size (Optional[int]) – block size of the PC

• alpha (Optional[torch.Tensor]) – optional transition parameters of size [num_latents, num_latents]

• beta (Optional[torch.Tensor]) – optional emission parameters of size [num_latents, num_emits]

• gamma (Optional[torch.Tensor]) – optional init parameters of size [num_latents]