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 Circuits01:25

Neural Circuits

2.0K
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...
2.0K
Improving Translational Accuracy02:07

Improving Translational Accuracy

12.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.1K
3.1K
Weighted Mean00:57

Weighted Mean

5.9K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
5.9K
Apparent Weight01:09

Apparent Weight

9.1K
True weight is the measure of the gravitational force acting on an object. However, if the object accelerates, its measured weight is different from its true weight. Similar observations can be made when the object is submerged in water. An object's weight in water is its apparent weight, which is equal to the difference between its true weight and the buoyant forces.
Consider a person standing on a bathroom scale inside an elevator. If the scale is accurate at rest, its reading equals the...
9.1K
Introduction to Learning01:18

Introduction to Learning

653
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...
653

You might also read

Related Articles

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

Sort by
Same author

In Situ Raman Spectroscopy Reveals the Dynamic Evolution and Ethanol Dependence of SEI Structure in Li-Mediated N<sub>2</sub> Reduction Reaction.

Journal of the American Chemical Society·2026
Same author

Sequencing Ablation and Systemic Therapy in Colorectal Liver Oligometastases: An Upfront versus Delayed Approach Nationwide Analysis.

Radiology·2026
Same author

HA thermostability mutations S84F, G167N, and D168N potentiate H9N2 virus transmission in a warming environment.

Emerging microbes & infections·2026
Same author

RNF213 isoform 2 restricts Zika virus through antiviral signaling and viral protein degradation.

iScience·2026
Same author

AirNet: A Deep Learning-Driven Auto Baseline Correction Algorithm Balancing Global Smoothness and Local Fidelity.

Analytical chemistry·2026
Same author

Efficient large-fragment isogenic sequence replacement in rice via prime editing with engineered reverse transcriptase variants.

Journal of advanced research·2026

Related Experiment Video

Updated: Nov 2, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices Based on Fine-Grained Structured

Wei Niu, Zhengang Li, Xiaolong Ma

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |June 16, 2021
    PubMed
    Summary

    This study introduces GRIM, a novel framework for accelerating deep neural network (DNN) inference on mobile devices. GRIM achieves real-time performance and high accuracy through structured sparsity and compiler optimizations, outperforming existing methods.

    Related Experiment Videos

    Last Updated: Nov 2, 2025

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.5K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Mobile Computing

    Background:

    • Mobile devices face challenges in executing large-scale deep neural networks (DNNs) due to resource constraints.
    • Achieving real-time DNN inference on mobile platforms requires efficient model compression techniques like weight pruning.
    • Existing DNN sparsity schemes often struggle to balance inference speed, accuracy, and mobile compatibility.

    Purpose of the Study:

    • To develop a novel mobile inference acceleration framework (GRIM) for deep neural networks (DNNs).
    • To enable real-time DNN inference on resource-constrained mobile devices while maintaining high model accuracy.
    • To design a new DNN weight sparsity scheme that is general to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

    Main Methods:

    • Proposed a fine-grained structured sparsity scheme called Block-based Column-Row (BCR) pruning.
    • Developed the GRIM framework integrating compiler optimizations and BCR pruning for mobile inference.
    • Implemented compiler optimization and code generation for real-time mobile execution.
    • Optimized BCR pruning for hyperparameter determination and weight pruning.

    Main Results:

    • The GRIM framework demonstrated significant speedups, achieving up to 14.08x compared to existing methods.
    • GRIM provides real-time inference capabilities for both CNNs and RNNs on mobile devices.
    • The proposed BCR pruning scheme effectively facilitates sparse model inference while preserving accuracy.

    Conclusions:

    • GRIM offers an effective solution for accelerating DNN inference on mobile devices.
    • The combination of fine-grained structured sparsity and compiler optimizations is crucial for efficient mobile AI.
    • GRIM represents a significant advancement in enabling complex DNN models to run efficiently on mobile platforms.