Disentangling the independently controllable factors of variation by interacting with the worldEI

    Cited by: 3|Bibtex|67|

    arXiv: Machine Learning, Volume abs/1802.094842018,

    Abstract:

    It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal ...More
    Your rating :
    0

     

    Tags
    Comments