Incremental training of first order recurrent neural networks to predict a context-sensitive language

32 citations recorded by the source corpus.

How researchers see this paper

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

Analysis Methods in Neural Language Processing: A Survey (2018, background): “A long tradition in work on neural networks is to evaluate and analyze their ability to learn different formal languages (Das et al., 1992; Casey, 1996; Gers and Schmidhuber, 2001; Bodén and Wiles, 2002; Chalup and Blair, 2003).”
Deep learning in neural networks: An overview (2014, background): “…next iteration; if there is an error et then δt := xt − dt ; add to δt the value k∈outt wv(t,k)δk; (this is the elegant and efficient recursive chain rule application collecting impacts of nett on future events) multiply δt by f ′t (nett); for all k ∈ int add to △wv(k,t) the value xkδt end for…”
Connectionist models of cognitive development: where next? (2005, background): “In these models, the advantages of a critical period for language learning result – counterintuitively – from processing limitations that occur in early childhood (see also [ 13 ,14] for related accounts).”
On Evaluating the Generalization of LSTM Models in Formal Languages (2018, methodology): “Following this approach, Bod´en and Wiles (2002) and Chalup and Blair (2003) studied the stability of the LSTM networks in learning context-free and context-sensitive languages and examined the processing mechanism developed by the hidden states during the training phase.”