Learning a context-free task with a recurrent neural network: An analysis of stability

How researchers see this paper

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

Deep learning in neural networks: An overview (2014, background): “LSTM also worked better on tasks involving context free languages (CFLs) that cannot be represented by HMMs or similar FSAs discussed in the RNN literature (Sun et al., 1993b; Wiles and Elman, 1995; Andrews et al., 1995; Steijvers and Grunwald, 1996; Tonkes and Wiles, 1997; Rodriguez et al., 1999; R”
Incremental training of first order recurrent neural networks to predict a context-sensitive language (2003, background): “Tonkes and Wiles (1999) suggested that the limited generalisation ability could model human performance when processing centre embedded sentences.”
Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, background): “The same algorithm has been used in various other contexts: as part of rule reﬁnement techniques (e.g. Omlin & Giles 1992, Giles & Omlin 1993, Das et al. 1993, Omlin & Giles 1996 c ), as an indicator of underlying language class (Blair & Pollack 1997), as a method for complexity evaluation (e.g. Bak”