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

Emergence of memory-driven command neurons in evolved artificial agents.

R Aharonov-Barki1, T Beker, E Ruppin

  • 1Center for Computational Neuroscience, The Hebrew University, Jerusalem, Israel.

Neural Computation
|March 13, 2001
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

The molecular cartography of malignant and benign sebaceous tumours.

Nature communications·2025
Same author

Tumor and blood B-cell abundance outperforms established immune checkpoint blockade response prediction signatures in head and neck cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2024
Same author

The tumour microenvironment shapes innate lymphoid cells in patients with hepatocellular carcinoma.

Gut·2021
Same author

The effects of telomere shortening on cancer cells: a network model of proteomic and microRNA analysis.

Genomics·2014
Same author

Common and specific signatures of gene expression and protein-protein interactions in autoimmune diseases.

Genes and immunity·2012
Same author

A systems level strategy for analyzing the cell death network: implication in exploring the apoptosis/autophagy connection.

Cell death and differentiation·2010

Autonomous agents with artificial neural networks (ANNs) achieved high performance in navigation and foraging. Evolution optimized ANNs by utilizing environmental features for efficient foraging.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Evolutionary Robotics

Background:

  • Autonomous agents require sophisticated control mechanisms for complex tasks.
  • Artificial neural networks (ANNs) offer a powerful framework for agent control.
  • Understanding the structure-function relationship in neural systems is a key challenge.

Purpose of the Study:

  • To develop and analyze autonomous agents controlled by evolved artificial neural networks (ANNs).
  • To investigate how sensory input influences neural control strategies in agents.
  • To model and understand the emergent properties of evolved neural controllers.

Main Methods:

  • Evolutionary simulations were used to train artificial neural networks (ANNs) for agent control.

Related Experiment Videos

  • Agents were tasked with foraging and navigation in simulated environments.
  • Experiments varied sensory input to analyze neural controller dynamics.
  • A two-parameter stochastic model was developed to capture memory mechanisms.

    • Main Results:

    • Fully recurrent ANN controllers enabled high performance in foraging and navigation.
    • A common command neuron structure was identified, switching between behavioral modes based on sensory input.
    • When position information was absent, a short-term memory mechanism drove behavior.
    • Evolved ANN parameters were near-optimal, demonstrating efficient use of environmental features.

    Conclusions:

    • Evolved ANNs provide a valuable model for studying neural control and structure-function relationships.
    • The findings offer insights into how neural networks adapt and utilize environmental information.
    • The study highlights the potential of evolutionary simulations in advancing artificial intelligence and neuroscience.