17 citations · 42 across the 13 of their papers we have counts for
Showing math.DSShow all
2 papers · 1 filter
math.DS2020★ 7 cited
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
Zahra Monfared, Daniel Durstewitz
Recurrent neural networks (RNN) as used in machine learning are commonly formulated in discrete time, i.e. as recursive maps. This brings a lot of advantages for training models on…
math.DS2019
Existence of n-cycles and border-collision bifurcations in piecewise-linear continuous maps with applications to recurrent neural networks
Zahra Monfared, Daniel Durstewitz
Piecewise linear recurrent neural networks (PLRNNs) form the basis of many successful machine learning applications for time series prediction and dynamical systems identification,…