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

Computing with dynamic attractors in neural networks

M W Hirsch1, B Baird

  • 1Department of Mathematics, University of California at Berkeley 94720-3840, USA.

Bio Systems
|January 1, 1995
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

Serum alkaline phosphatase and mortality in hemodialysis patients.

Clinical nephrology·2010
Same author

Gamma-ray imaging with a Si/CsI(Tl) Compton detector.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2006
Same author

Symposium: A Celebration of Reproductive Rights: Twenty-Five Years of Roe v. Wade.

Women's rights law reporter·2005
Same author

Crosslinking a lipid raft component triggers liquid ordered-liquid disordered phase separation in model plasma membranes.

Proceedings of the National Academy of Sciences of the United States of America·2005
Same author

The effects of list difficulty and modality of presentation on a computerized version of the Paced Serial Addition Test (PSAT).

Journal of clinical and experimental neuropsychology·2004
Same author

Abortion, questions, ethics, embodiment.

History workshop journal : HWJ·2002
Same journal

The impedance mismatch theory: A non-equilibrium thermodynamic framework for a shared energetic stress pathway in neurodegeneration.

Bio Systems·2026
Same journal

Immune signal-status misclassification: A theoretical framework for biological status assignment and failed status resolution.

Bio Systems·2026
Same journal

Contextuality, incompatibility, and intra-system entanglement of mental markers: From cognition and decision making to medicine.

Bio Systems·2026
Same journal

A unified clearance-based model of homeostatic drive across acute and chronic sleep loss.

Bio Systems·2026
Same journal

Pattern regeneration in two-dimensional cellular automata models of bivalve shell symmetry.

Bio Systems·2026
Same journal

The formation of the quantum entanglement in DNA-mRNA system.

Bio Systems·2026
See all related articles

This study introduces novel neural network architectures inspired by the brain, utilizing dynamic attractors for computation. These models explore integrating analog and digital processing for enhanced cognitive tasks.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Neuroscience

Background:

  • Neural computation often uses fixed-point attractors.
  • Brain activity exhibits complex dynamics, including oscillations and chaos.
  • Human brain capabilities may stem from integrated analog and digital processing.

Purpose of the Study:

  • To develop new neural network architectures inspired by biological systems.
  • To explore computation using arbitrary attractors (oscillatory/chaotic) alongside fixed points.
  • To investigate the potential of richer network dynamics for cognitive tasks.

Main Methods:

  • Constructed a parallel distributed processing architecture.
  • Modeled the architecture on the structure and dynamics of the cerebral cortex.

Related Experiment Videos

  • Used ordinary differential equations for network dynamics, aiming for anatomical and dynamical faithfulness.

    • Main Results:

    • Demonstrated neural networks can compute with arbitrary attractors.
    • Developed an architecture inspired by coupled associative memories with dynamic attractors.
    • The architecture is designed for reliable computation in noisy environments.

    Conclusions:

    • Richer dynamics in recurrent networks are likely beneficial for computation.
    • Complex nervous systems may inherently involve chaotic dynamics.
    • The developed architecture offers a pathway to replicate brain-like cognitive functions.