144 citations · 177 across the 3 of their papers we have counts for
Showing cs.NEShow all
2 papers · 1 filter
cs.NE2018★ 3 cited
State-Denoised Recurrent Neural Networks
Michael C. Mozer, Denis Kazakov, Robert V. Lindsey
Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccurac…
cs.NE2017★ 30 cited
Discrete Event, Continuous Time RNNs
Michael C. Mozer, Denis Kazakov, Robert V. Lindsey
We investigate recurrent neural network architectures for event-sequence processing. Event sequences, characterized by discrete observations stamped with continuous-valued times of…