Higher Order Recurrent Networks and Grammatical Inference

By C. Lee Giles, Guo-Zheng Sun, Hsing-Hen Chen, Yee-Chun Lee, Dong Chen. 1989

How researchers see this paper

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

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “Early examples of memory-augmented RNNs (Das et al., 1992; Mozer and Das, 1993) use a continuous adaptation of stacks based on the differentiable push and pop operations introduced by Giles et al. (1990) (cf. Joulin and Mikolov, 2015 for an alternative implementation).”
TerpreT: A Probabilistic Programming Language for Program Induction (2016, background): “These include Recurrent Neural Networks (RNNs) augmented with a stack or queue memory (Giles et al., 1989; Joulin and Mikolov, 2015; Grefenstette et al., 2015), Neural Turing Machines (Graves et al.”
The Induction of Dynamical Recognizers (1991, background): “I end the paper with a hypothesis relating linguistic generative capacity to the behavioral regimes of non-linear dynamical systems.”
Time Warping Invariant Neural Networks (1992, methodology): “In our early work of [4,5,6], to train a NNFA (Neural Network Finite Automaton), we used a discrete mapping”
Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference (2001, background): “In the past few years several recurrent neural network architectures have emerged which have been used for grammatical inference (Cleeremans et al., 1989; Giles et al., 1992; Giles et al., 1990).”
Long-term Forecasting using Tensor-Train RNNs (2017, background): “In principle, early work (Giles et al., 1989) has shown that with a large enough hidden state size, such recurrent structures are capable of approximating any dynamics.”
Induction of Finite-State Automata Using Second-Order Recurrent Networks (1991, methodology): “The problem of inducing languages from examples has also been approached using second-order recurrent networks (Pollack, 1990; Giles et al., 1990).”
Combining Symbolic and Neural Learning (1994, background): “Cleermans, Servan-Schreiber, and McClelland (1989) and Giles et al. (1992) have a different perspective.”
Neural Functional Programming (2016, background): “A related line of research is the extension of neural network architectures with components that correspond to hardware primitives (Giles et al., 1989; Graves et al., 2014; Weston et al., 2015; Joulin & Mikolov, 2015; Grefenstette et al., 2015; Kurach et al., 2016; Kaiser & Sutskever, 2016; Reed &…”
Long-term Forecasting using Higher Order Tensor RNNs (2017, methodology): “he most recent state. Our method contrasts with this by explicitly modeling higher-order dyanmics to capture long-term dependencies. There are several classic work on higher-order RNNs. For example, (Giles et al., 1989) proposes a higher-order RNN to simulate a deterministic nite state machine and r”