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

Neuroplasticity

Neuroplasticity

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.

You might also read

Related Articles

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

Sort by

Same journal

Impact of room configuration on energy use intensity in high-density pilgrim accommodations: a case study in Makkah, Saudi Arabia.

Scientific reports·2026

Same journal

Retraction Note: Improving the power production efficiency of microbial fuel cell by using biosynthesized polyanaline coated Fe<sub>3</sub>O<sub>4</sub> as pencil graphite anode modifier.

Scientific reports·2026

Same journal

Stylopine as multi-target anti-Alzheimer agent.

Scientific reports·2026

Same journal

Principal component analysis of morphological features of the aortic arch for predicting the risk for acute type B aortic dissection.

Scientific reports·2026

Same journal

An explainable AfroXLMR approach for multi-label emotion classification of Amharic social media text with dataset release.

Scientific reports·2026

Same journal

Bridging in vitro bioactivities and in silico insights of Rubia cordifolia L. (Rubiaceae) leaf extracts for therapeutic applications.

Scientific reports·2026

Search research articles

Related Experiment Video

Updated: Jul 4, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Resource constrained neural network training.

Mariusz Pietrołaj¹, Marek Blok²

¹Faculty of Electronics, Telecommunications, and Informatics, Gdansk University of Technology, Gdańsk, Poland. mariusz.pietrolaj@pg.edu.pl.

Scientific Reports

|January 29, 2024

Summary

This summary is machine-generated.

This study refines neural network parameter limitation for edge AI. Using an asymmetric exponent method, researchers trained models with 8-bit floating-point precision, maintaining performance comparable to 32-bit systems.

More Related Videos

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

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

Published on: March 2, 2015

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Published on: October 13, 2019

Related Experiment Videos

Last Updated: Jul 4, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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

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

Published on: March 2, 2015

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Training Dogs for Awake, Unrestrained Functional Magnetic Resonance Imaging

Published on: October 13, 2019

Area of Science:

Artificial Intelligence
Computer Science
Machine Learning

Background:

Modern AI applications are shifting to resource-constrained edge devices.
This necessitates efficient neural network training methods to reduce computational and power demands.
Existing parameter bit-count reduction techniques primarily focus on inference, not training.

Purpose of the Study:

To develop and evaluate a novel method for limiting neural network parameters during training.
To investigate advanced techniques for floating-point variable representation and rounding.
To achieve efficient neural network training without significant performance degradation.

Main Methods:

Implementation of an asymmetric exponent method for parameter limitation.
Exploration of new floating-point variable representation and rounding strategies.
Utilizing exponent offset for floating-point precision adjustments without increasing bit count.

Main Results:

Successfully trained LeNet, AlexNet, and ResNet-18 convolutional neural networks using a custom 8-bit floating-point representation.
Achieved minimal to no degradation in performance compared to baseline 32-bit floating-point training.
Demonstrated the feasibility of resource-efficient neural network training.

Conclusions:

The asymmetric exponent method offers an effective approach for reducing resource requirements in neural network training.
8-bit floating-point precision can be utilized for training complex models with comparable accuracy to 32-bit.
This research enables more cost-efficient AI model development and broader AI application on personal devices.