Field Guide to Dynamical Recurrent Networks

By S. C. Kremer, John F. Kolen. 2001

269 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Pieter Abbeel
3. Yoshua Bengio
4. Chelsea Finn
5. Ruslan Salakhutdinov
6. J. Urgen Schmidhuber
7. Yuxi Li
8. Quoc V. Le

In Computational Theory and Mathematics

1. Sergey Levine
2. Nicolas Manfred Otto Heess
3. Joel Veness
4. Hado van Hasselt
5. Razvan Pascanu
6. Nando de Freitas
7. Yee Whye Teh
8. Mark Rowland

Citations in the corpus

• Meta-learning of Sequential Strategies (2019, methodology): “If we use a memory-based architecture, such as a recurrent neural network [Elman, 1990, Jordan, 1997, Hochreiter et al., 2001, Kolen and Kremer, 2001, Graves, 2012], then the function f conforms to the interface where π t ∈ ∆( X ) is the current prediction vector, m t and m t − 1 ∈ M are the…”
• Pre-training of Recurrent Neural Networks via Linear Autoencoders (2014, background): “Recurrent Neural Networks (RNN) constitute a powerful computational tool for sequences modelling and prediction [1].”
• Forecasting with Recurrent Neural Networks: 12 Tricks (2012, background): “Overshooting extends the autonomous system dynamics (coded matrix A) into the future (here t + 2, t + 3, t + 4)[18] (see Fig.”
• Diffusion Probabilistic Modeling for Video Generation (2022, methodology): “For a practical scheme involving multiple time steps, we also employ teacher forcing [79].”
• Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, methodology): “The choice of q is however usually not explicitly described as part of the RE algorithm (one exception is in the description by Omlin (2001) where the suggested incremental procedure is also part of the algorithm).”
• Long-term time series prediction with the NARX network: An empirical evaluation (2008, background): “Even though feedforward multilayer perceptron (MLP)-like networks can be easily adapted to process time series through an input tapped-delay line, giving rise to the well-known time delay neural network (TDNN) [36], they can also be easily converted to SRNs by feeding back the neuronal outputs of th”
• Learning Long Term Dependencies with Recurrent Neural Networks (2006, unknown): “Recurrent neural networks (RNNs) allow the identification of dynamical systems in form of high dimensional, nonlinear state space models [1, 2 ].”