Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Observational Learning

Observational Learning

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...

Associative Learning

Associative Learning

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...

Introduction to Learning

Introduction to Learning

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...

Generalization, Discrimination, and Extinction

Generalization, Discrimination, and Extinction

Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

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...

You might also read

Related Articles

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

Sort by

Same author

A wholistic view of continual learning with deep neural networks: Forgotten lessons and the bridge to active and open world learning.

Neural networks : the official journal of the International Neural Network Society·2023

Same author

Return of the normal distribution: Flexible deep continual learning with variational auto-encoders.

Neural networks : the official journal of the International Neural Network Society·2022

Same author

Real-time traffic sign recognition based on a general purpose GPU and deep-learning.

PloS one·2017

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition.

Martin Mundt¹, Iuliia Pliushch¹, Sagnik Majumder²

¹Department of Computer Science and Mathematics, Goethe University, 60323 Frankfurt am Main, Germany.

Journal of Imaging

|April 21, 2022

Summary

This study introduces a probabilistic method using variational inference to improve deep neural network robustness. It helps distinguish unknown data and reduces knowledge loss in continual learning systems.

Keywords:

catastrophic forgetting continual deep learning deep generative models open-set recognition variational inference

Related Experiment Videos

Last Updated: Sep 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Artificial Intelligence
Machine Learning
Deep Learning

Background:

Deep neural networks (DNNs) exhibit brittleness when encountering novel data instances.
Recognizing and handling these unknown data instances remains a significant challenge in AI.
Continual learning systems inevitably face unseen concepts, yet research often prioritizes mitigating interference over unknown data detection.

Purpose of the Study:

To develop a unified probabilistic approach for enhancing DNN robustness against unknown data.
To enable the distinction between known and unknown (out-of-distribution) data.
To simultaneously address catastrophic interference in continual learning.

Main Methods:

A probabilistic approach based on variational inference within a single deep autoencoder model.
Bounding the approximate posterior by fitting high-density regions of correctly classified data.
Utilizing these bounds for distinguishing out-of-distribution data and refining generative replay.

Main Results:

The proposed bounds effectively distinguish unseen, out-of-distribution data from known tasks.
This distinction contributes to more robust applications of deep learning models.
Generative replay, when narrowed to in-distribution samples, significantly alleviates catastrophic interference.

Conclusions:

The probabilistic approach offers a dual benefit: robust out-of-distribution detection and reduced catastrophic interference.
This method enhances the reliability and adaptability of deep neural networks in dynamic environments.
It provides a foundational step towards more resilient and continuously learning AI systems.