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

339
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...
339
Associative Learning01:27

Associative Learning

617
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...
617
Survival Tree01:19

Survival Tree

170
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
170
Introduction to Learning01:18

Introduction to Learning

567
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...
567
Cognitive Learning01:21

Cognitive Learning

680
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
680
Neural Regulation01:37

Neural Regulation

40.4K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.4K

You might also read

Related Articles

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

Sort by
Same author

Corrigendum to "Metformin prevents mandibular bone loss in a mouse model of accelerated aging by correcting dysregulated AMPK-mTOR signaling and osteoclast differentiation" [J Orthop Transl 46 (2024) 129-142].

Journal of orthopaedic translation·2026
Same author

A chromosome-level reference genome assembly of the King Ratsnake (Elaphe carinata).

Scientific data·2026
Same author

Epithelial and Interstitial Gli2 Activation Correlates With Renal Tubulointerstitial Fibrosis and Facilitates FoxM1-Associated Myofibroblast Phenotypic Transition.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
Same author

Electronic and steric effects of phosphine ligands on the linear regioselectivity of propylene methoxycarbonylation.

Communications chemistry·2026
Same author

Unsupervised Anomaly Detection in Medical Imaging: A Survey of Methods, Challenges, and Future Directions.

Bioengineering (Basel, Switzerland)·2026
Same author

Impact of Mono-, Di-, and Trivalent Ions on the Rheology of Borate-Crosslinked Guar Fracturing Fluids.

Gels (Basel, Switzerland)·2026

Related Experiment Video

Updated: Sep 24, 2025

Author Spotlight: Advancing Alzheimer's Research – 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

1.3K

Learning Deep Neural Networks under Agnostic Corrupted Supervision.

Boyang Liu1, Mengying Sun1, Ding Wang1

  • 1Department of Computer Science, Michigan State University.

Proceedings of Machine Learning Research
|May 3, 2022
PubMed
Summary

This study introduces a robust algorithm for training deep neural models with corrupted data, focusing on controlling collective gradient impact rather than individual data point loss. The method ensures data quality and enhances model generalization without assumptions on corruption type.

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.5K

Related Experiment Videos

Last Updated: Sep 24, 2025

Author Spotlight: Advancing Alzheimer's Research – 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

1.3K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.5K

Area of Science:

  • Machine Learning
  • Deep Learning
  • Artificial Intelligence

Background:

  • Training deep neural models with corrupted supervision poses significant challenges to generalization performance.
  • Existing methods often rely on filtering data points based on individual loss values, which can be insufficient.

Purpose of the Study:

  • To develop an efficient and robust algorithm for training deep neural models with corrupted supervision.
  • To provide a unified framework applicable to both classification and regression tasks.
  • To achieve strong theoretical guarantees without assumptions on the type of data corruption.

Main Methods:

  • The proposed algorithm focuses on controlling the collective impact of data points on the average gradient.
  • It offers a unified framework for classification and regression problems.
  • The method does not rely on quantifying individual data point quality or loss values for filtering.

Main Results:

  • The algorithm demonstrates robustness under various corruption types across multiple benchmark datasets.
  • Corrupted data points have a limited impact on the overall loss, even if not entirely excluded.
  • Achieves strong generalization performance despite the presence of corrupted supervision.

Conclusions:

  • The developed algorithm offers an effective solution for handling corrupted supervision in deep learning.
  • Its focus on collective gradient impact provides superior robustness compared to loss-based filtering methods.
  • The unified framework enhances its applicability across diverse machine learning tasks.