Neural network processing of natural language: I. Sensitivity to serial, temporal and abstract structure of language in the infant

By Peter Ford Dominey, Franck Ramus. 2000

114 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology

View Paper: https://www.semanticscholar.org/paper/f7a3e53d1677c23f7462d8d54bd93579d26d9e29

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

In Developmental and Educational Psychology

Citations in the corpus

Introduction to spiking neural networks: Information processing, learning and applications. (2011, background): “The concept of reservoir computing has initially been suggested in the context of non-spiking ANN (Atiya and Parlos 2000, Dominey and Ramus 2000, Jaeger 2001, Steil 2004).”
Doing without schema hierarchies: a recurrent connectionist approach to normal and impaired routine sequential action. (2004, background): “Of some relevance in this regard is the work of Dominey (e.g., Dominey, 1998; Dominey & Ramus, 2000 ), in which sequential networks are trained using a version of reinforcement learning.”
A Practical Guide to Applying Echo State Networks (2012, background): “It should be noted that this basic idea was first clearly spelled out in a neuroscientific model of the corticostriatal processing loop [9].”
Reservoir Computing Trends (2012, background): “for modeling parts of sensory-motor sequence [8] and speech [10] learning architectures have been employed even before the original ESN and LSM publications.”
Indeterminacy in language acquisition: the role of child directed speech and joint attention (2004, background): “Dominey and Ramus (2000) had previously demonstrated that the TRN could exploit prosodic structure in consonant –vowel sequences in order to discriminate between languages from different rhythmic classes.”
Reservoir computing approaches to recurrent neural network training (2009, background): “Second, adaptation is based on a simple associative learning mechanism (... )” [50].”
Recent Advances in Physical Reservoir Computing: A Review (2018, background): “…model (called a temporal recurrent network) for learning serial and temporal structure of sequential inputs with an additional abstract recurrent network which has a short term memory for encoding an abstract structure (or a hidden rule) of sequential inputs (Dominey & Ramus, 2000).”