Stack-like and queue-like dynamics in recurrent neural networks

DOI10.1080/09540090500317291zbMATH Open1084.68097OpenAlexW2158191188MaRDI QIDQ3375554FDOQ3375554

André Grüning

Publication date: 14 March 2006

Published in: Connection Science (Search for Journal in Brave)

Full work available at URL: http://epubs.surrey.ac.uk/22858/2/gruening_05_connection_science.pdf

zbMATH Keywords

formal languagesnetwork dynamicsdynamical complexitysimple current networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM
• Three models for the description of language
• Symbolic dynamics. One-sided, two-sided and countable state Markov shifts
• A logical calculus of the ideas immanent in nervous activity
• Rules and arithmetics
• On the computational power of neural nets
• QRT FIFO automata, breadth-first grammars and their relations
• The calculi of emergence: Computation, dynamics and induction
• Spatiotemporal connectionist networks: A taxonomy and review
• Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review
• Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
• Architectural Bias in Recurrent Neural Networks: Fractal Analysis
• Dynamical recognizers: real-time language recognition by analog computers
• Simple recurrent networks learn context-free and context-sensitive languages by counting.
• Why it might pay to assume that languages are infinite
• Learning the dynamics of embedded clauses

Cited In (4)

• Simple recurrent networks learn context-free and context-sensitive languages by counting.
• Learning the dynamics of embedded clauses
• Elman Backpropagation as Reinforcement for Simple Recurrent Networks
• \(G\)-networks: A unifying model for neural and queueing networks

Uses Software

• LSTM

   Recommendations

• Simple recurrent networks learn context-free and context-sensitive languages by counting. 👍 👎
• Organization of the state space of a simple recurrent network before and after training on recursive linguistic structures 👍 👎
• Learning the dynamics of embedded clauses 👍 👎
• Elements for a general memory structure: properties of recurrent neural networks used to form situation models 👍 👎
• Comparing simple recurrent networks and \(n\)-grams in a large corpus 👍 👎

This page was built for publication: Stack-like and queue-like dynamics in recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3375554)