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

Classification of Systems-II01:31

Classification of Systems-II

127
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
127
Classification of Systems-I01:26

Classification of Systems-I

161
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
161
Aggregates Classification01:29

Aggregates Classification

291
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
291
Confidence Coefficient01:24

Confidence Coefficient

7.4K
The confidence coefficient is also known as the confidence level or degree of confidence. It is the percent expression for the probability, 1-α, that the confidence interval contains the true population parameter assuming that the confidence interval is obtained after sufficient unbiased sampling; for example, if the CL = 90%, then in 90 out of 100 samples the interval estimate will enclose the true population parameter. Here α is the area under the curve, distributed equally under...
7.4K
Classification of Signals01:30

Classification of Signals

348
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
348
Force Classification01:22

Force Classification

1.1K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.1K

You might also read

Related Articles

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

Sort by
Same author

Synthesis, in vitro and in vivo biological evaluation, and comprehensive understanding of structure-activity relationships of dipeptidyl boronic acid proteasome inhibitors constructed from β-amino acids.

Journal of medicinal chemistry·2010
Same author

Evaluation of the association between the AC3 genetic polymorphisms and obesity in a Chinese Han population.

PloS one·2010
Same author

Structure of yeast regulatory subunit: a glimpse into the evolution of PKA signaling.

Structure (London, England : 1993)·2010
Same author

[Effect of Rhizoma Coptidis coadministration with Cortex Cinnamomi on tissue distribution of berberine in rats].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2010
Same author

Exosomal-like vesicles with immune-modulatory features are present in human plasma and can induce CD4+ T-cell apoptosis in vitro.

Transfusion·2010
Same author

Qualitative analysis and simultaneous quantification of phenolic compounds in the aerial parts of Salvia miltiorrhiza by HPLC-DAD and ESI/MS(n).

Phytochemical analysis : PCA·2010

Related Experiment Video

Updated: May 15, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

Multi-head ensemble of smoothed classifiers for certified robustness.

Kun Fang1, Qinghua Tao2, Yingwen Wu1

  • 1Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 10, 2025
PubMed
Summary

SmOothed Multi-head Ensemble (SOME) enhances certified robustness in Deep Neural Networks (DNNs) by training a single network with multiple heads. This approach achieves state-of-the-art performance with significantly reduced computational costs compared to traditional ensembles.

Keywords:
Certified robustnessCo-teachingEnsembleRandomized smoothingSelf-paced learning

More Related Videos

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

Related Experiment Videos

Last Updated: May 15, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Randomized Smoothing (RS) is a key technique for certified robustness in Deep Neural Networks (DNNs).
  • Ensembling multiple DNNs improves RS performance but incurs substantial computational overhead.
  • Existing ensemble methods often overlook the synergistic potential and communication between individual networks.

Purpose of the Study:

  • To introduce a novel, computationally efficient method for achieving certified robustness using an ensemble approach.
  • To develop a training strategy that maximizes the benefits of ensembling within a single DNN architecture.
  • To improve both the effectiveness and efficiency of certifiably robust defenses in DNNs.

Main Methods:

  • Proposed SmOothed Multi-head Ensemble (SOME), a single DNN with multiple augmented heads trained using a cosine constraint.
  • Implemented a circular communication flow and self-paced learning strategy among heads using smoothed losses.
  • Designed losses specifically for certified robustness and to encourage diversity among heads.

Main Results:

  • SOME demonstrates competitive or superior certifiably-robust performance compared to ensembling multiple DNNs.
  • The multi-head architecture and circular-teaching scheme significantly reduce training and certification computational costs.
  • Achieved a more effective and efficient defense against adversarial attacks through ensemble benefits within a single model.

Conclusions:

  • The SOME approach offers a highly effective and computationally efficient solution for certified robustness in DNNs.
  • The novel training strategy and architecture successfully leverage ensemble effects while mitigating computational burdens.
  • SOME represents a significant advancement in developing practical and scalable certifiably robust machine learning models.