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

Reducing Line Loss01:18

Reducing Line Loss

184
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
184
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.8K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.8K
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.7K
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...
11.7K
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

121
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
121
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

620
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
620
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

88
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...
88

You might also read

Related Articles

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

Sort by
Same author

Reduction of Vision-Based Models for Fall Detection.

Sensors (Basel, Switzerland)·2024
Same author

A Generalization Performance Study Using Deep Learning Networks in Embedded Systems.

Sensors (Basel, Switzerland)·2021
Same author

Non-Invasive Ambient Intelligence in Real Life: Dealing with Noisy Patterns to Help Older People.

Sensors (Basel, Switzerland)·2019
Same author

Smart Meeting Room Usage Information and Prediction by Modelling Occupancy Profiles.

Sensors (Basel, Switzerland)·2019
Same author

Enhancing Confusion Entropy (CEN) for binary and multiclass classification.

PloS one·2019

Related Experiment Video

Updated: Aug 7, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

SLRProp: A Back-Propagation Variant of Sparse Low Rank Method for DNNs Reduction.

Asier Garmendia-Orbegozo1, Jose David Nuñez-Gonzalez1, Miguel Angel Anton2

  • 1Department of Applied Mathematics, University of the Basque Country UPV/EHU, 20600 Eibar, Spain.

Sensors (Basel, Switzerland)
|March 11, 2023
PubMed
Summary

Deep neural networks (DNNs) in edge computing require parameter reduction. This study introduces Sparse Low Rank (SLR) methods, including SLRProp, to maintain DNN accuracy while reducing model size for real-time applications.

Keywords:
deep learningedge computingpruning

More Related Videos

Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.7K
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

596

Related Experiment Videos

Last Updated: Aug 7, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.7K
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

596

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Edge Computing

Background:

  • Deep neural networks (DNNs) are crucial for real-time edge computing but require significant parameters.
  • Reducing DNN complexity is essential for efficient deployment on edge devices.

Purpose of the Study:

  • To investigate methods for reducing the size of DNNs used in edge computing.
  • To evaluate the impact of parameter reduction techniques on network accuracy and performance.

Main Methods:

  • Application of the Sparse Low Rank (SLR) method to Fully Connected (FC) layers.
  • Proposal of SLRProp, a variant considering inter-layer neuron relevancies.
  • Experimental validation on established DNN architectures.

Main Results:

  • SLR method applied to FC layers to assess its impact on network response.
  • SLRProp variant demonstrated a method to weigh component relevancies across layers.
  • Experimental results compared intra-layer vs. inter-layer relevancy effects on network output.

Conclusions:

  • The study explored parameter reduction techniques for DNNs in edge computing.
  • SLR and SLRProp methods were proposed and evaluated for their effectiveness.
  • Findings suggest that inter-layer relevancy considerations may influence network response differently than intra-layer methods.