language-icon Old Web
English
Sign In

Training recurrent networks

1997 
Training recurrent networks is generally believed to be a difficult task. Excessive training times and lack of convergence to an acceptable solution are frequently reported. In this paper we seek to explain the reason for this from a numerical point of view and show how to avoid problems when training. In particular we investigate ill-conditioning, the need for and effect of regularization and illustrate the superiority of second-order methods for training.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    9
    References
    9
    Citations
    NaN
    KQI
    []