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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

52
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
52

You might also read

Related Articles

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

Sort by
Same author

PsychiatryBench: a multi-task benchmark for LLMs in psychiatry.

NPJ digital medicine·2026
Same author

Efficient and real-time perception: a survey on end-to-end event-based object detection in autonomous driving.

Frontiers in robotics and AI·2025
Same author

Chimera: a block-based neural architecture search framework for event-based object detection.

Frontiers in artificial intelligence·2025
Same author

A recurrent YOLOv8-based framework for event-based object detection.

Frontiers in neuroscience·2025
Same author

Amphibious epidermal area networks for uninterrupted wireless data and power transfer.

Nature communications·2023
Same author

Efficient training of spiking neural networks with temporally-truncated local backpropagation through time.

Frontiers in neuroscience·2023

Related Experiment Video

Updated: Jun 27, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.1K

A Review of State-of-the-art Mixed-Precision Neural Network Frameworks.

Mariam Rakka, Mohammed E Fouda, Pramod Khargonekar

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 29, 2024
    PubMed
    Summary

    Mixed-precision Deep Neural Networks (DNNs) optimize hardware deployment by efficiently managing bit precision for each layer. This survey reviews current frameworks for DNN quantization, aiding researchers in navigating this complex search space.

    More Related Videos

    Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
    10:45

    Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

    Published on: May 31, 2017

    13.1K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    524

    Related Experiment Videos

    Last Updated: Jun 27, 2025

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

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.1K
    Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling
    10:45

    Anatomically Inspired Three-dimensional Micro-tissue Engineered Neural Networks for Nervous System Reconstruction, Modulation, and Modeling

    Published on: May 31, 2017

    13.1K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    524

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Deep Neural Networks (DNNs) require significant computational resources for deployment.
    • Mixed-precision DNNs offer a solution by reducing resource demands while preserving accuracy.
    • Determining optimal layer-wise bit precision is complex due to numerous variables.

    Purpose of the Study:

    • To provide a comprehensive overview of standard quantization classifications in DNNs.
    • To survey and comparatively analyze existing mixed-precision DNN frameworks.
    • To identify the strengths and weaknesses of current approaches.

    Main Methods:

    • Literature review of existing studies on DNN quantization.
    • Classification of standard quantization techniques.
    • Comparative analysis of prominent mixed-precision DNN frameworks.

    Main Results:

    • Categorization of prevalent quantization classifications.
    • Detailed survey of current mixed-precision frameworks.
    • Highlighting of merits and limitations of each framework.

    Conclusions:

    • Mixed-precision DNNs are crucial for efficient hardware deployment.
    • The current landscape of frameworks presents diverse solutions and challenges.
    • Future research should explore novel approaches to optimize mixed-precision DNNs.