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

Neuroplasticity01:01

Neuroplasticity

325
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.
325
Introduction to Learning01:18

Introduction to Learning

360
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
360
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

739
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
739
Neural Circuits01:25

Neural Circuits

1.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.1K

You might also read

Related Articles

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

Sort by
Same author

Density-mediated freshwater plastisphere microbiomes preferentially degrade conventional rather than biodegradable microplastics.

The ISME journal·2026
Same author

<i>Asplenium yishuiensis</i> (Aspleniaceae), a New Wintergreen and Medicinal Fern from Northern China, Achieves Freezing Tolerance via a Calcium-Mediated Osmotic Adjustment Pathway.

Plants (Basel, Switzerland)·2026
Same author

Augmenting clinical decision-making with large language models: evaluation across general and specialty tasks.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Regional surveillance of non-A-F Salmonella enterica reveals diverse risk profiles, with global genomic insights from Salmonella Worthington.

Food research international (Ottawa, Ont.)·2026
Same author

Optimal selection of ovarian stimulation protocol for infertile women with diminished ovarian reserve based on Bologna and POSEIDON criteria: a network meta-analysis.

Reproductive biology and endocrinology : RB&E·2026
Same author

From lipid dysbalance to cardiorenal decompensation: apoB/ApoA1 ratio is associated with acute cardiorenal injury in CAD patients.

Frontiers in cardiovascular medicine·2026

Related Experiment Video

Updated: Jun 24, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K

Machine unlearning in brain-inspired neural network paradigms.

Chaoyi Wang1, Zuobin Ying1, Zijie Pan1

  • 1Faculty of Data Science, City University of Macau, Macao, Macao SAR, China.

Frontiers in Neurorobotics
|June 5, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a hybrid machine unlearning method for Spiking Neuron Models (SNMs). The approach effectively removes data while maintaining or improving AI model performance, enhancing privacy and compliance.

Keywords:
brain-inspired ANNscomputer visiondata securitymachine learningprivacy protectionspiking neural networks

More Related Videos

Author Spotlight: Unveiling Neural Mechanisms Through Automated Evaluation of Motor Learning and Myelin Plasticity Studies Using the Erasmus Ladder
08:51

Author Spotlight: Unveiling Neural Mechanisms Through Automated Evaluation of Motor Learning and Myelin Plasticity Studies Using the Erasmus Ladder

Published on: December 15, 2023

1.3K
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.7K

Related Experiment Videos

Last Updated: Jun 24, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.3K
Author Spotlight: Unveiling Neural Mechanisms Through Automated Evaluation of Motor Learning and Myelin Plasticity Studies Using the Erasmus Ladder
08:51

Author Spotlight: Unveiling Neural Mechanisms Through Automated Evaluation of Motor Learning and Myelin Plasticity Studies Using the Erasmus Ladder

Published on: December 15, 2023

1.3K
An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.7K

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Machine unlearning is vital for data privacy and regulatory adherence in AI.
  • Spiking Neuron Models (SNMs) mimic biological neural networks, offering potential for efficient AI.
  • Implementing unlearning in SNMs is challenging but necessary for ethical AI deployment.

Purpose of the Study:

  • To develop and evaluate a novel hybrid machine unlearning approach for Spiking Neuron Models (SNMs).
  • To ensure effective removal of specific data while preserving overall model integrity and performance.
  • To enhance the flexibility and ethical compliance of AI models utilizing SNMs.

Main Methods:

  • A hybrid machine unlearning strategy combining selective synaptic retraining, synaptic pruning, and adaptive neuron thresholding was developed.
  • The approach was implemented and tested on Spiking Neuron Models (SNMs).
  • Experiments were conducted using diverse computer vision datasets to evaluate performance metrics.

Main Results:

  • The proposed hybrid unlearning method successfully eliminated targeted information from SNMs.
  • Critical performance metrics, including accuracy, precision, recall, and ROC AUC, were preserved or improved post-unlearning.
  • The approach demonstrated practicality and efficiency in maintaining neural network integrity.

Conclusions:

  • The hybrid machine unlearning approach is effective for Spiking Neuron Models (SNMs).
  • This method enhances AI flexibility and ethical compliance without compromising performance.
  • The findings support the applicability of this unlearning technique in real-world AI systems.