Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Neural Circuits

Neural Circuits

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...

Transformers with Off-Nominal Turns Ratios

Transformers with Off-Nominal Turns Ratios

In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the rated...

You might also read

Related Articles

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

Sort by

Same author

Augmenting Performance Status: A Preliminary Study of Objective Kinematic Assessment Using Motion Capture.

Oncology and therapy·2026

Same author

Multi-resolution modeling of a discrete stochastic process identifies causes of cancer.

... International Conference on Learning Representations·2026

Same author

Verifiably stable nonlinear control with reinforcement-learned diffractive optical networks.

Optics express·2026

Same author

Dissociating Contributions of Theta and Alpha Oscillations from Aperiodic Neural Activity in Human Visual Working Memory.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2026

Same author

Unsupervised Representation Learning From Sparse Transformation Analysis.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

CellSAM: a foundation model for cell segmentation.

Nature methods·2025

Search research articles

Related Experiment Video

Updated: May 8, 2026

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

Population Transformer: Learning Population-level Representations of Neural Activity.

Geeling Chau, Christopher Wang, Sabera Talukder

|June 17, 2024

Summary

We developed a Population Transformer (PopT) for scalable neural decoding. This self-supervised framework improves accuracy and reduces data needs for analyzing neural population activity across diverse datasets.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Published on: January 19, 2024

Related Experiment Videos

Last Updated: May 8, 2026

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Live Imaging Followed by Single Cell Tracking to Monitor Cell Biology and the Lineage Progression of Multiple Neural Populations

Published on: December 16, 2017

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Author Spotlight: Comparative Imaging of Neural Activity in Awake and Freely Moving States

Published on: January 19, 2024

Area of Science:

Neuroscience
Machine Learning
Computational Biology

Background:

Scaling neural decoding models is challenging due to sparse and variable electrode data across subjects and datasets.
Existing methods often require extensive data and computational resources for training.
Integrating information from multiple, spatially-sparse neural recording channels remains a significant hurdle.

Purpose of the Study:

To introduce a self-supervised framework, the Population Transformer (PopT), for learning population-level neural codes at scale.
To enhance downstream decoding performance by effectively aggregating information from sparse neural data channels.
To reduce the data requirements and computational load for neural decoding tasks.

Main Methods:

Developed the Population Transformer (PopT) by stacking on pretrained temporal embeddings.
Implemented a learned aggregation mechanism for multiple, spatially-sparse neural data channels.
Utilized a self-supervised learning approach for training the model on large-scale neural recordings.

Main Results:

The pretrained PopT significantly lowered data requirements for downstream decoding while increasing accuracy, even on held-out subjects and tasks.
Achieved comparable or superior decoding performance to end-to-end methods with a computationally lightweight approach.
Demonstrated generalizability across multiple time-series embeddings and neural data modalities.
Showcased the interpretability of PopT models for extracting neuroscience insights.

Conclusions:

The Population Transformer (PopT) offers a scalable and efficient solution for population-level neural decoding.
This framework improves decoding accuracy and reduces data needs, making it valuable for analyzing large-scale neural recordings.
PopT facilitates the extraction of neuroscience insights and enables off-the-shelf improvements in multi-channel intracranial data decoding and interpretability.