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

Observational Learning01:12

Observational Learning

329
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
329
Classification of Systems-II01:31

Classification of Systems-II

245
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,
245
Classification of Systems-I01:26

Classification of Systems-I

334
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:
334
Classification of Signals01:30

Classification of Signals

940
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...
940
Introduction to Learning01:18

Introduction to Learning

556
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...
556
Aggregates Classification01:29

Aggregates Classification

395
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...
395

You might also read

Related Articles

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

Sort by
Same author

COX-2 inhibition improves immune system homeostasis and decreases liver damage in septic rats.

The Journal of surgical research·2009
Same author

Mass spectral characterization of organophosphate-labeled, tyrosine-containing peptides: characteristic mass fragments and a new binding motif for organophosphates.

Journal of chromatography. B, Analytical technologies in the biomedical and life sciences·2009
Same author

3D-SURFER: software for high-throughput protein surface comparison and analysis.

Bioinformatics (Oxford, England)·2009
Same author

Total arch replacement with stented elephant trunk technique: a proposed treatment for complicated Stanford type B aortic dissection.

Journal of cardiac surgery·2009
Same author

Top-emitting white organic light-emitting devices with a one-dimensional metallic-dielectric photonic crystal anode.

Optics letters·2009
Same author

[Detection of tick and tick-borne pathogen in some ports of Inner Mongolia].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2009
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: Sep 22, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

577

Epoch-Evolving Gaussian Process Guided Learning for Classification.

Jiabao Cui, Xuewei Li, Hanbin Zhao

    IEEE Transactions on Neural Networks and Learning Systems
    |May 23, 2022
    PubMed
    Summary
    This summary is machine-generated.

    Epoch-evolving Gaussian Process Guided Learning (GPGL) enhances deep learning by encoding global data distribution. This novel method overcomes mini-batch limitations, improving convergence and outperforming existing optimization techniques.

    Related Experiment Videos

    Last Updated: Sep 22, 2025

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    577

    Area of Science:

    • Machine Learning
    • Deep Learning
    • Optimization Algorithms

    Background:

    • Conventional mini-batch gradient descent algorithms often get stuck in local optima due to limited batch-level distribution information, causing a "zig-zag" learning effect.
    • Characterizing the correlation between batch-level and global data distributions is crucial for efficient deep learning optimization.

    Purpose of the Study:

    • To propose a novel learning scheme, epoch-evolving Gaussian Process Guided Learning (GPGL), that encodes global data distribution information non-parametrically.
    • To improve the convergence speed and efficiency of deep learning models by addressing the limitations of traditional gradient descent methods.

    Main Methods:

    • GPGL utilizes a Gaussian Process (GP) model built upon class-aware anchor samples to estimate class distributions (context labels) for mini-batch samples via label propagation.
    • The estimated context labels complement ground-truth one-hot labels, providing smooth, context-rich information to guide the optimization process.
    • A triangle consistency loss is employed to update model parameters, leveraging both context and ground-truth labels for efficient optimization.

    Main Results:

    • The GPGL scheme effectively encodes global data distribution information in a non-parametric manner.
    • The proposed method demonstrates a smooth class distribution structure that accelerates the convergence process.
    • GPGL was successfully generalized and applied to current deep models, outperforming state-of-the-art optimization methods on six benchmark datasets.

    Conclusions:

    • GPGL offers a significant advancement in deep learning optimization by mitigating the "zig-zag" effect associated with conventional methods.
    • The integration of context labels derived from Gaussian Processes provides a robust mechanism for enhancing model training efficiency and performance.
    • The proposed GPGL scheme is a versatile and effective approach applicable to various deep learning architectures, setting a new benchmark in optimization performance.