Recurrent Orthogonal Networks and Long-Memory Tasks

Henaff, Mikael, Szlam, Arthur, LeCun, Yann

arXiv.org Artificial Intelligence 

Although RNNs have been shown to be powerful tools for processing sequential data, finding architectures or optimization strategies that allow them to model very long term dependencies is still an active area of research. In this work, we carefully analyze two synthetic datasets originally outlined in (Hochreiter and Schmidhuber, 1997) which are used to evaluate the ability of RNNs to store information over many time steps. We explicitly construct RNN solutions to these problems, and using these constructions, illuminate both the problems themselves and the way in which RNNs store different types of information in their hidden states. These constructions furthermore explain the success of recent methods that specify unitary initializations or constraints on the transition matrices.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilarity
None found