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

Neural Regulation01:37

Neural Regulation

43.1K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
43.1K
Approximate Integration01:24

Approximate Integration

4
In many practical and theoretical contexts, the exact value of a definite integral may be inaccessible. This limitation typically arises when the antiderivative of a function is either unknown or cannot be expressed in a closed mathematical form. Alternatively, it can occur when a function is defined not by a formula but by a finite set of empirical data points, such as those collected during experiments. In these cases, approximate integration techniques provide a valuable solution.One of the...
4
PI Controller: Design01:24

PI Controller: Design

1.2K
Proportional Integral (PI) controllers are a fundamental component in modern control systems, widely used to enhance performance and mitigate steady-state errors. They are particularly effective in applications such as automatic brightness adjustment on smartphones, where they excel at mitigating steady-state errors for step-function inputs. Unlike PD controllers, which require time-varying errors to function optimally, PI controllers leverage their integral component to address residual...
1.2K
Applications of Integration to Probability Density Functions01:27

Applications of Integration to Probability Density Functions

4
Continuous probability distributions are used to model random variables that can take on any real value within a specified range. These variables do not take on isolated or countable values but rather exist on a continuum. For example, the height of an individual can be measured with increasing precision—such as 163.5 or 165.25 centimeters—demonstrating that height is a continuous random variable.The behavior of such variables is described using a probability density function (PDF),...
4

You might also read

Related Articles

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

Sort by
Same author

Rapid neuronal labeling and functional imaging in the developing mouse brain with AAV-PHP.eB.

Cell reports methods·2026
Same author

Serum magnesium is associated with osteoporosis risk in postmenopausal women: a retrospective study and risk-prediction model.

Frontiers in medicine·2026
Same author

Multi-omics reveals different signatures of obesity-prone and obesity-resistant mice.

iMetaOmics·2026
Same author

An antioxidant, injectable hydrogel with mitochondrial fusion effect promotes inflamed dental pulp repair via immunomodulation and reactive oxygen species scavenging.

Biomaterials·2026
Same author

Hyodeoxycholic Acid Suppresses High-Fat-Diet-Promoted MC38-Syngeneic Colorectal Tumor Growth via Bile Acid Remodeling and Microbiota Modulation.

Nutrients·2025
Same author

S100A9 inhibition ameliorates HFpEF by modulating mitochondrial fission and oxidative stress.

International immunopharmacology·2025

Related Experiment Videos

Lightweight Reparameterizable Integral Neural Networks for Mobile Applications.

Jinhua Lin, Xin Li, Bowen Ren

    IEEE Transactions on Neural Networks and Learning Systems
    |October 27, 2025
    PubMed
    Summary
    This summary is machine-generated.

    We introduce lightweight reparameterizable integral neural networks (RINNs) for mobile devices. These RINNs efficiently handle continuous integration layers, achieving high accuracy with low latency on ImageNet.

    Related Experiment Videos

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Standard integral neural networks (INNs) face deployment challenges on mobile devices due to their complex structure.
    • The reparameterization problem in continuous integration layers hinders efficient inference.

    Purpose of the Study:

    • To address the deployment limitations of INNs on resource-constrained mobile devices.
    • To develop a novel class of lightweight and efficient neural networks.

    Main Methods:

    • Proposed a continuous reparameterization strategy to convert training-time integration layers into an inference-time feed-forward structure.
    • Extended the MetaFormer (Vision Transformer-like) architecture for continuous integration layers.
    • Introduced an overparameterization integral branch to enhance representation capacity.

    Main Results:

    • Developed lightweight reparameterizable INNs (RINNs) with strong performance on mobile devices.
    • Achieved over 79.1% top-1 accuracy with 0.87 ms latency on ImageNet.
    • Demonstrated superior robustness to structural pruning compared to discrete models.

    Conclusions:

    • RINNs offer a promising solution for deploying advanced neural networks on mobile platforms.
    • The proposed methods enable efficient and accurate deep learning inference in resource-limited environments.