Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Modelling of syntactical processing in the cortex.

Heiner Markert1, Andreas Knoblauch, Günther Palm

  • 1Department of Neural Information Processing, University of Ulm, Oberer Eselsberg, D-89069 Ulm, Germany. heiner.markert@uni-ulm.de

Bio Systems
|February 6, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comparing Surrogates to Evaluate Precisely Timed Higher-Order Spike Correlations.

eNeuro·2022
Same author

Power Function Error Initialization Can Improve Convergence of Backpropagation Learning in Neural Networks for Classification.

Neural computation·2021
Same author

Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations.

Frontiers in robotics and AI·2021
Same author

Detection and evaluation of bursts in terms of novelty and surprise.

Mathematical biosciences and engineering : MBE·2019
Same author

Iterative Retrieval and Block Coding in Autoassociative and Heteroassociative Memory.

Neural computation·2019
Same author

Toward Self-Referential Autonomous Learning of Object and Situation Models.

Cognitive computation·2016

This study proposes a neural network model for understanding human language, integrating syntax and semantics. The model demonstrates context awareness and can learn new words, advancing artificial intelligence in natural language processing.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Computational Linguistics

Background:

  • Explaining human language processing, particularly syntax-semantics interplay, is a significant challenge in brain function theories.
  • Limited animal models and difficulties in studying human neural processing necessitate novel theoretical approaches.

Purpose of the Study:

  • To present a neural network architecture for understanding semantico-syntactical structures in human language.
  • To demonstrate the model's capability for context awareness and runtime learning of new object words.

Main Methods:

  • Utilizing well-established basic neural mechanisms within a global network architecture.
  • Formulating the architecture in terms of cortical areas and their interconnections.
  • Implementing the system to process and understand language input.

Related Experiment Videos

Main Results:

  • The neural network successfully masters the logical task of understanding semantico-syntactical structures.
  • The model exhibits context awareness, correcting ambiguous input (e.g., 'bot show/lift green wall' interpreted as 'bot show green wall').
  • The system demonstrates the ability to learn new object words during runtime.

Conclusions:

  • A plausible neural network architecture can effectively model intricate language processing, including syntax and semantics.
  • The proposed model offers a step towards understanding context awareness and adaptive learning in artificial language systems.
  • This approach provides a framework for further research into the neural basis of language comprehension.