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

Elaborative Rehearsals01:07

Elaborative Rehearsals

88
Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...
88
Chunking and Rehearsal in Sensory Memory01:22

Chunking and Rehearsal in Sensory Memory

215
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of...
215
Downsampling01:20

Downsampling

159
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
159
Stream Function01:20

Stream Function

1.5K
In two-dimensional incompressible fluid flow, the continuity equation is essential for ensuring mass conservation, meaning that any change in fluid entering or exiting a region is balanced by a corresponding change elsewhere. For incompressible flow, where density remains constant, this requirement simplifies to the condition that the divergence of the velocity field must be zero. Mathematically, this is expressed as,
1.5K
Sampling Plans01:23

Sampling Plans

187
Sampling is a crucial step in analytical chemistry, allowing researchers to collect representative data from a large population. Common sampling methods include random, judgmental, systematic, stratified, and cluster sampling.
Random sampling is a method where each member of the population has an equal chance of being selected for the sample. It involves selecting individuals randomly, often using random number generators or lottery-type methods. For example, when analyzing the properties of a...
187
Sampling Continuous Time Signal01:11

Sampling Continuous Time Signal

251
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
251

You might also read

Related Articles

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

Sort by
Same author

Computational and mathematical models in vision: Quantitative approaches to understanding visual perception.

Vision research·2026
Same author

Unraveling the geometry of visual relational reasoning.

Scientific reports·2026
Same author

Order-Selective Cells Tile Temporal Space and Predict Order Memory in Humans.

bioRxiv : the preprint server for biology·2025
Same author

Comorbid anxiety predicts lower odds of MDD improvement in a trial of smartphone-delivered interventions.

Journal of affective disorders·2025
Same author

Behavioral relevance of category selectivity revealed by human ECoG data.

PloS one·2025
Same author

Single-neuron encoding of rapidly learned visual information reshapes human perception.

bioRxiv : the preprint server for biology·2025
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: Jul 7, 2025

Automated Interactive Video Playback for Studies of Animal Communication
07:21

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

13.6K

Tuned Compositional Feature Replays for Efficient Stream Learning.

Morgan B Talbot, Rushikesh Zawar, Rohil Badkundri

    IEEE Transactions on Neural Networks and Learning Systems
    |December 25, 2023
    PubMed
    Summary
    This summary is machine-generated.

    Artificial neural networks struggle with continual learning, but a new algorithm, CRUMB (compositional replay using memory blocks), mitigates catastrophic forgetting by reconstructing and replaying feature maps, improving knowledge retention in stream learning.

    More Related Videos

    Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
    11:20

    Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

    Published on: June 2, 2014

    12.0K
    Tuning a Parallel Segmented Flow Column and Enabling Multiplexed Detection
    08:01

    Tuning a Parallel Segmented Flow Column and Enabling Multiplexed Detection

    Published on: December 15, 2015

    7.4K

    Related Experiment Videos

    Last Updated: Jul 7, 2025

    Automated Interactive Video Playback for Studies of Animal Communication
    07:21

    Automated Interactive Video Playback for Studies of Animal Communication

    Published on: February 9, 2011

    13.6K
    Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning
    11:20

    Recording Single Neurons' Action Potentials from Freely Moving Pigeons Across Three Stages of Learning

    Published on: June 2, 2014

    12.0K
    Tuning a Parallel Segmented Flow Column and Enabling Multiplexed Detection
    08:01

    Tuning a Parallel Segmented Flow Column and Enabling Multiplexed Detection

    Published on: December 15, 2015

    7.4K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • Artificial neural networks (ANNs) exhibit limitations in extracting generalizable knowledge from sequential data, unlike human brains.
    • Standard ANNs trained on shuffled data suffer catastrophic forgetting when learning new information in temporal order (online stream learning).

    Purpose of the Study:

    • To introduce a novel continual learning algorithm, compositional replay using memory blocks (CRUMB), designed to mitigate catastrophic forgetting in ANNs.
    • To enhance the ability of ANNs to retain knowledge from past experiences while learning new stimuli in a continuous stream.

    Main Methods:

    • CRUMB reconstructs feature maps by combining generic parts stored in trainable and reusable "memory blocks" within convolutional neural networks (CNNs).
    • The algorithm stores indices of memory blocks to enable replay of stimuli during later tasks, biasing networks towards shape information and stabilizing training.
    • CRUMB was evaluated against 13 competing methods on seven datasets, including two newly adapted benchmarks for online stream learning.

    Main Results:

    • CRUMB significantly outperforms existing methods in mitigating catastrophic forgetting, achieving superior performance with substantially less memory (3.6% of a comparable image-replaying algorithm).
    • The algorithm demonstrates effectiveness with minimal memory overhead (3.7%-4.1%) and comparable runtime (15%-43%) compared to state-of-the-art methods.
    • CRUMB provides a stable, shared feature-level basis for training examples, enhancing generalization and reducing the impact of new, unseen data.

    Conclusions:

    • CRUMB presents a highly effective and memory-efficient solution for continual learning in ANNs, addressing the critical challenge of catastrophic forgetting.
    • The compositional reconstruction of feature maps offers a promising direction for developing more robust and adaptable artificial intelligence systems.
    • The proposed method significantly advances the field of online stream learning and provides a valuable tool for AI research and development.