86 citations · 340 across the 10 of their papers we have counts for
3 papers · 1 filter
AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
Bo Chang, Minmin Chen, Eldad Haber +1
Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or v…
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
Minmin Chen, Jeffrey Pennington, Samuel S. Schoenholz
Recurrent neural networks have gained widespread use in modeling sequence data across various domains. While many successful recurrent architectures employ a notion of gating, the…
Cost-Sensitive Tree of Classifiers
Zhixiang Xu, Matt J. Kusner, Kilian Q. Weinberger +1
Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e.g. search engines and email spam filters). Here, the CPU cost duri…