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 Concept Videos

Neurogenesis and Regeneration of Nervous Tissue01:15

Neurogenesis and Regeneration of Nervous Tissue

956
In the CNS, neurogenesis, the birth of new neurons from stem cells, is limited to the hippocampus in adults. In other regions of the brain and spinal cord, neurogenesis is almost non-existent due to inhibitory influences from neuroglia, especially oligodendrocytes, and the absence of growth-stimulating cues. The myelin produced by oligodendrocytes in the CNS inhibits neuronal regeneration. Furthermore, astrocytes proliferate rapidly after neuronal damage, forming scar tissue that physically...
956
Neuroplasticity01:01

Neuroplasticity

681
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
681

You might also read

Related Articles

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

Sort by
Same author

Event-Based Vision at the Edge: A Review.

Brain sciences·2026
Same author

Can I Do Better Than AI: A Comparative Analysis of a Medical Student Essay Created With and Without Generative AI.

Cureus·2026
Same author

Building on models-a perspective for computational neuroscience.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Learning long sequences in spiking neural networks.

Scientific reports·2024
Same author

Editorial: Hardware for artificial intelligence.

Frontiers in neuroscience·2022
Same author

Beyond LIF Neurons on Neuromorphic Hardware.

Frontiers in neuroscience·2022
Same journal

Logic, inference, understanding: cross-domain generalization for generative language models.

Frontiers in artificial intelligence·2026
Same journal

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026
Same journal

Score-based generative diffusion models to synthesize full-dose FDG brain PET from MRI in epilepsy patients.

Frontiers in artificial intelligence·2026
Same journal

Resource-efficient retrieval-augmented question answering for the Indian Lok Sabha dataset.

Frontiers in artificial intelligence·2026
Same journal

Violation detection in power operation sites based on multi-scale detection and few-shot learning.

Frontiers in artificial intelligence·2026
Same journal

Deep reinforcement learning-based reversible medical image encryption framework for secure IoMT environments.

Frontiers in artificial intelligence·2026
See all related articles

Related Experiment Video

Updated: Aug 21, 2025

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices
07:44

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Published on: October 6, 2017

17.4K

Error driven synapse augmented neurogenesis.

Adam Perrett1, Steve B Furber1, Oliver Rhodes1

  • 1Department of Computer Science, The University of Manchester, Manchester, United Kingdom.

Frontiers in Artificial Intelligence
|November 17, 2022
PubMed
Summary
This summary is machine-generated.

The novel Error Driven Neurogenesis (EDN) algorithm enables artificial intelligence to learn instantly, mimicking human capabilities. This biologically plausible approach significantly outperforms gradient descent in speed and error reduction across various tasks.

Keywords:
classificationneurogenesisone-shotregressionreinforcement learningsynaptic activation

More Related Videos

Assaying Circuit Specific Regulation of Adult Hippocampal Neural Precursor Cells
08:52

Assaying Circuit Specific Regulation of Adult Hippocampal Neural Precursor Cells

Published on: July 24, 2019

6.5K
Quantifying Synapses: an Immunocytochemistry-based Assay to Quantify Synapse Number
18:11

Quantifying Synapses: an Immunocytochemistry-based Assay to Quantify Synapse Number

Published on: November 16, 2010

35.9K

Related Experiment Videos

Last Updated: Aug 21, 2025

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices
07:44

Evaluation of Synapse Density in Hippocampal Rodent Brain Slices

Published on: October 6, 2017

17.4K
Assaying Circuit Specific Regulation of Adult Hippocampal Neural Precursor Cells
08:52

Assaying Circuit Specific Regulation of Adult Hippocampal Neural Precursor Cells

Published on: July 24, 2019

6.5K
Quantifying Synapses: an Immunocytochemistry-based Assay to Quantify Synapse Number
18:11

Quantifying Synapses: an Immunocytochemistry-based Assay to Quantify Synapse Number

Published on: November 16, 2010

35.9K

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Current artificial intelligence learning models, like gradient descent, rely on parameter updates to minimize errors.
  • Human learning is characterized by rapid, one-shot knowledge acquisition and immediate application, a capability not fully replicated in current AI.
  • Parametric models capture statistical data properties but lack the biological plausibility of immediate, online learning.

Purpose of the Study:

  • To introduce the Error Driven Neurogenesis (EDN) algorithm, a novel approach for one-shot, online learning in artificial intelligence.
  • To demonstrate a biologically plausible mechanism for immediate data storage and task application without parameter updates.
  • To compare the performance of EDN against traditional gradient descent methods in various machine learning tasks.

Main Methods:

  • The study presents the Error Driven Neurogenesis (EDN) algorithm, incorporating neurogenesis and non-linear synaptic activations.
  • EDN enables immediate data storage and application in a one-shot, online fashion, bypassing the need for iterative parameter updates.
  • The algorithm was tested on regression (auto-mpg), wine cultivar classification, MNIST image recognition, and reinforcement learning (inverted pendulum) tasks.

Main Results:

  • EDN reduced regression test error over 135 times faster and achieved a three times smaller error compared to gradient descent with ADAM optimization.
  • In wine cultivar classification, EDN reached performance levels 25 times faster than gradient descent.
  • EDN demonstrated superior speed, achieving comparable performance twice as fast as gradient descent on MNIST and the inverted pendulum tasks.

Conclusions:

  • The Error Driven Neurogenesis (EDN) algorithm offers a biologically plausible and highly efficient alternative to gradient-based learning.
  • EDN facilitates immediate, one-shot learning and task application, significantly accelerating AI performance.
  • This neurogenesis-inspired approach has the potential to revolutionize artificial intelligence by enabling faster and more adaptable learning capabilities.