Variational Temporal AbstractionEI

    Taesup Kim
    Taesup Kim
    Sungjin Ahn
    Sungjin Ahn
    Click here to see all papers in nips2019
    Cited by: 0|Bibtex|50|

    NeurIPS, pp. 11566-11575, 2019.

    Abstract:

    We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state transition hierarchi...More
    Your rating :
    0

     

    Tags
    Comments