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

Associative Learning01:27

Associative Learning

878
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
878
Introduction to Learning01:18

Introduction to Learning

706
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...
706
Dot Product: Problem Solving01:21

Dot Product: Problem Solving

563
The dot product is a powerful tool in problem-solving involving vectors, given that the dot product of two vectors is the product of their magnitudes and the cosine of the angle between them measured anti-clockwise. Solving problems involving the dot product requires understanding its properties and developing a step-by-step process to solve them. Here are the main steps to follow when solving any general problem involving the dot product:
Identify the problem: Start by reading the problem and...
563
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

265
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
265
Collisions in Multiple Dimensions: Problem Solving01:06

Collisions in Multiple Dimensions: Problem Solving

4.9K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
4.9K
Observational Learning01:12

Observational Learning

641
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...
641

You might also read

Related Articles

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

Sort by
Same author

Human-AI Cooperation in Healthcare and Rehabilitation.

Delaware journal of public health·2026
Same author

Training sparse convolutional deep predictive coding networks with attention.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

<i>Mannheimia kashgarensis</i> sp. nov., isolated from the nasopharynx of sheep with ovine respiratory disease.

International journal of systematic and evolutionary microbiology·2026
Same author

Knittable, thermally insulating, and sustainable aerogel fibers enabled by ion-mediated hierarchical assembly.

Nature communications·2026
Same author

Electroacupuncture as a promising therapeutic strategy for chronic constriction injury-induced neuropathic pain: Insights into the PPARα/SIRT1/NF-κB axis.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Multi-omics Analysis Reveals Comprehensive Aberrant Protein and Phosphorylation Characteristics in Breast Cancer and Paired Metastatic Lymph Nodes.

Protein & cell·2026
Same journal

ASSR-Net: Anisotropic Structure-Aware and Spectrally Recalibrated Network for Hyperspectral Image Fusion.

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

PIMPC-GNN: Physics-Informed Multiphase Consensus Learning for Enhancing Imbalanced Node Classification in Graph Neural Networks.

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

Quantum Rényi α-Entropies for Graph Characterization.

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

LANet: A Lightweight and Accurate Balanced Network Based on State Space Models for Real-Time Semantic Segmentation.

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

MENDNet: Memory-Enhanced Dependency Network for Multistock Movement Prediction.

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

Temporal Mask-Embedding Learning and Query-Refined Head Network for Visual Tracking.

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

Related Experiment Video

Updated: Nov 23, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

Modularizing Deep Learning via Pairwise Learning With Kernels.

Shiyu Duan, Shujian Yu, Jose C Principe

    IEEE Transactions on Neural Networks and Learning Systems
    |January 5, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study redefines deep neural networks (DNNs) as stacked linear models, introducing a modular learning framework that requires only weak supervision for hidden layers. This approach achieves high accuracy with minimal labeled data, enhancing DNN workflow efficiency and model reusability.

    More Related Videos

    Decoding Natural Behavior from Neuroethological Embedding
    08:00

    Decoding Natural Behavior from Neuroethological Embedding

    Published on: October 3, 2025

    310

    Related Experiment Videos

    Last Updated: Nov 23, 2025

    Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
    09:47

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

    Published on: December 15, 2023

    1.5K
    Decoding Natural Behavior from Neuroethological Embedding
    08:00

    Decoding Natural Behavior from Neuroethological Embedding

    Published on: October 3, 2025

    310

    Area of Science:

    • Machine Learning
    • Deep Learning Theory
    • Kernel Methods

    Background:

    • Conventional deep neural networks (DNNs) rely on extensive labeled data and complex backpropagation.
    • Understanding the theoretical underpinnings of DNNs, particularly their layer structure and label requirements, remains an active research area.

    Purpose of the Study:

    • To propose a novel interpretation of finitely wide, fully trainable DNNs as stacked linear models in feature spaces, akin to kernel machines.
    • To introduce a provably optimal modular learning framework for classification that bypasses the need for between-module backpropagation.
    • To investigate the label efficiency and workflow advantages of modular deep learning.

    Main Methods:

    • Redefining DNN layers to establish a kernel machine interpretation.
    • Developing a modular learning framework that utilizes implicit pairwise labels (weak supervision) for hidden modules.
    • Employing full supervision for the output module, focusing on label efficiency with minimal examples.
    • Proposing a method for estimating module reusability and task transferability in transfer learning.

    Main Results:

    • Achieved 94.88% accuracy on CIFAR-10 using a ResNet-18 backbone with only ten randomly selected labeled examples.
    • Demonstrated that the modular approach requires only weak supervision for hidden layers.
    • Showcased simplified, maintainable, and reusable deep learning workflows.
    • Accurately described the task space structure of 15 binary classification tasks from CIFAR-10 with minimal computational overhead.

    Conclusions:

    • The proposed modular learning framework offers a new perspective on deep learning, reducing label dependency and enhancing workflow modularity.
    • This approach provides significant label efficiency and improves the reusability and maintainability of deep learning models.
    • The kernel machine interpretation and modular design offer theoretical insights and practical benefits for deep learning applications.