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

You might also read

Related Articles

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

Sort by
Same author

Integrated RNA-seq and ATAC-seq analysis of miR-101 in bovine somatic cell reprogramming.

Genomics·2026
Same author

Top-down motivation both decreases and increases feature interference following a saccade.

Psychonomic bulletin & review·2026
Same author

The Application of 3D Printing in Cardiac Patch Manufacture.

Advanced healthcare materials·2026
Same author

Myelin damage in major depressive disorder: Insights from neuroimaging, molecular mechanisms, and therapeutic perspectives.

Neuroscience and biobehavioral reviews·2026
Same author

Human EEG and artificial neural networks reveal disentangled representations and processing timelines of object real-world size and depth in natural images.

eLife·2025
Same author

An ultrathin gas-permeable imperceptible electronic skin enables maxillofacial electrophysiological monitoring.

Journal of materials chemistry. B·2025

Related Experiment Video

Updated: Feb 22, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.3K

Achieving more human brain-like vision via human EEG representational alignment.

Zitong Lu1,2, Yile Wang3, Julie D Golomb4

  • 1Department of Psychology, The Ohio State University, Columbus, OH, USA. zitonglu@mit.edu.

Communications Biology
|February 20, 2026
PubMed
Summary

This study introduces Re(presentational)Al(ignment)net, a novel AI vision model using non-invasive EEG data to better mimic human brain visual processing. The model shows improved alignment with human brain representations, advancing artificial intelligence.

More Related Videos

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.3K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.8K

Related Experiment Videos

Last Updated: Feb 22, 2026

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

15.3K
Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients
07:43

Simultaneous Eye Tracking and Single-Neuron Recordings in Human Epilepsy Patients

Published on: June 17, 2019

8.3K
SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots
11:01

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

13.8K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Computer Vision

Background:

  • Current object recognition models struggle to replicate human brain visual processing.
  • Existing methods often use invasive neural recordings, limiting human brain studies.
  • A gap exists in understanding human visual perception using neural data.

Purpose of the Study:

  • To develop a vision model aligned with human brain activity using non-invasive EEG data.
  • To create an innovative image-to-brain multi-layer encoding framework.
  • To enhance the mimicry of human brain visual representational patterns.

Main Methods:

  • Developed 'Re(presentational)Al(ignment)net' (ReAlnet), a vision model utilizing non-invasive EEG.
  • Implemented an image-to-brain multi-layer encoding framework.
  • Optimized multiple model layers for efficient learning of human visual patterns.

Main Results:

  • ReAlnet demonstrated significantly higher similarity to human brain representations compared to traditional models.
  • Achieved an average similarity improvement of approximately 3%.
  • Reached a maximum relative improvement ratio of up to 40% in mimicking brain representations.

Conclusions:

  • The ReAlnet framework advances human neural alignment in AI vision models.
  • This approach effectively learns and mimics human brain visual representational patterns.
  • The study represents a significant step towards brain-like artificial intelligence and bridging the gap between artificial and human vision.