Skip to main content

Vocabulary of natural language processing

Search from vocabulary

Concept information

Preferred term

neural networks model  

Definition

  • Computational model that consists of several processing elements that receive inputs and deliver outputs based on their predefined activation functions. (Science Direct)

Broader concept

Synonym(s)

  • ANN
  • artificial neural network
  • connectionist model

Definitional context(s)

  • Artificial neural networks (ANNs) are powerful computational models that are able to implicitly learn syntactic and semantic features necessary for a variety of natural language tasks. (Kann, Warstadt, Williams & Bowman, 2019)

Example

  • An artificial neural network (ANN) with multiple hidden layers also called a Deep Neural Network (DNN) try to mimic the deep architecture of the brain and it is believed to perform better than shallow architectures such as logistic regression models and ANNs without hidden units. (Liu & Inkpen, 2015)
  • Classification can also be done within connectionist models. (Weng, 1991)
  • Given the computational cost of computing n-gram probabilities with neural network models a solution is to resort to a two-pass approach: the first pass uses a conventional system to produce a k-best list (the k most likely hypotheses); in the second pass probabilities are computed by the SOUL models for each hypothesis and added as new features. (Do, Herrmann, Niehues, Allauzen, Yvon & Waibel, 2014)
  • One artificial neural network in which connections between the neuron units do not form a cycle is a feed-forward neural network (FNN). (Talukdar, Sarma & Bhuyan, 2023)
  • We implemented an artificial neural network with a single hidden layer composed of 500 nodes. (Badgett & Huang, 2016)

In other languages

URI

http://data.loterre.fr/ark:/67375/8LP-FZXXSFHX-G

Download this concept:

RDF/XML TURTLE JSON-LD Last modified 5/15/24