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

Multicompartment Models: Overview01:14

Multicompartment Models: Overview

408
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
408
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

307
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...
307
Observational Learning01:12

Observational Learning

713
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...
713
Associative Learning01:27

Associative Learning

987
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...
987
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.4K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.4K
Purposive Learning01:22

Purposive Learning

336
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
336

You might also read

Related Articles

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

Sort by
Same author

Meta-Modulation: A General Learning Framework for Cross-Task Adaptation.

IEEE transactions on neural networks and learning systems·2024
Same author

Study on Allele Specific Expression of Long-Term Residents in High Altitude Areas.

Evolutionary bioinformatics online·2024
Same author

Weak Augmentation Guided Relational Self-Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

A Theoretical View of Linear Backpropagation and its Convergence.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Bipartite Ranking Fairness Through a Model Agnostic Ordering Adjustment.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Automatically Predicting Material Properties with Microscopic Images: Polymer Miscibility as an Example.

Journal of chemical information and modeling·2023

Related Experiment Video

Updated: Dec 12, 2025

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

2.7K

Model-Protected Multi-Task Learning.

Jian Liang, Ziqi Liu, Jiayu Zhou

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |August 12, 2020
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel privacy-preserving multi-task learning (MTL) framework to prevent model information leakage between tasks. The new approach ensures models do not underperform compared to single-task learning (STL) methods.

    More Related Videos

    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen
    07:52

    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

    Published on: October 5, 2020

    3.8K
    Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
    07:42

    Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

    Published on: December 16, 2022

    3.4K

    Related Experiment Videos

    Last Updated: Dec 12, 2025

    Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
    05:23

    Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

    Published on: March 11, 2021

    2.7K
    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen
    07:52

    Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

    Published on: October 5, 2020

    3.8K
    Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
    07:42

    Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

    Published on: December 16, 2022

    3.4K

    Area of Science:

    • Machine Learning
    • Artificial Intelligence
    • Computer Security

    Background:

    • Multi-task learning (MTL) trains models on multiple related tasks simultaneously, leveraging shared information for improved performance over single-task learning (STL).
    • A significant security concern in MTL is the potential for information leakage between tasks, where an adversary can exploit one task to gain access to models of other tasks.
    • Existing privacy-preserving MTL methods primarily focus on data instance protection and may suffer performance degradation compared to STL.

    Purpose of the Study:

    • To propose a novel privacy-preserving multi-task learning (MTL) framework designed to prevent model information leakage across different tasks.
    • To ensure the proposed MTL algorithms maintain performance parity with single-task learning (STL) methods.
    • To provide robust privacy guarantees using differential privacy tools, including utility bounds and consideration of heterogeneous privacy budgets.

    Main Methods:

    • The proposed framework perturbs the covariance matrix of the model matrix to prevent information leakage between models.
    • The approach is instantiated for two common MTL methods: learning low-rank and group-sparse patterns within the model matrix.
    • Differential privacy principles are employed to establish formal privacy guarantees and derive utility bounds.

    Main Results:

    • Experimental results demonstrate that the proposed algorithms outperform baseline methods that use existing privacy-preserving MTL techniques.
    • The algorithms effectively prevent information leakage from one model to another within the MTL framework.
    • The developed methods achieve performance comparable to or better than single-task learning (STL) approaches.

    Conclusions:

    • The novel privacy-preserving MTL framework effectively mitigates model information leakage risks.
    • The proposed methods offer strong privacy guarantees while maintaining competitive or superior performance compared to STL and existing privacy-preserving MTL techniques.
    • This work advances the field of secure and efficient multi-task learning.