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

Improving Translational Accuracy02:07

Improving Translational Accuracy

9.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.0K
Associative Learning01:27

Associative Learning

289
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...
289
Long-term Potentiation01:25

Long-term Potentiation

2.7K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
2.7K
Survival Tree01:19

Survival Tree

60
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...
60
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

440
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...
440
Aggregates Classification01:29

Aggregates Classification

303
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
303

You might also read

Related Articles

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

Sort by
Same author

Surface-Neutralized HgCdSe Quantum Dots for High-Detectivity Infrared Photodetectors.

Nano letters·2026
Same author

Wired and Wireless Photosynthetic Biohybrids: Design, Materials, and Mechanisms.

Chemical reviews·2026
Same author

Precision pathophysiology in steatotic liver disease.

Clinical and molecular hepatology·2026
Same author

Quantum Dot Encoding for In-Solution Single-Molecule Biomarker Counting in Metastatic Prostate Cancer.

ACS nano·2026
Same author

Mesothelin/Mucin 16 Signaling in Activated Portal Fibroblasts Drives the Development of Cholestatic Fibrosis and Hepatocellular Carcinoma in Aged Female Multidrug Resistance Protein 2 Knockout Mice.

Cellular and molecular gastroenterology and hepatology·2026
Same author

MIrROR release 02: Expanded and refined 16S-ITS-23S rRNA operon dataset.

Scientific data·2026

Related Experiment Video

Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502

Improving forward compatibility in class incremental learning by increasing representation rank and feature richness.

Jaeill Kim1, Wonseok Lee2, Moonjung Eo3

  • 1LINE Investment Technologies, 117 Bundangnaegok-ro, Bundang-gu, Seongnam-si, 13529, South Korea.

Neural Networks : the Official Journal of the International Neural Network Society
|December 8, 2024
PubMed
Summary

We introduce the Feature Richness enhancement (RFR) method to improve forward compatibility in Class Incremental Learning (CIL). RFR enhances novel task performance and mitigates catastrophic forgetting by increasing feature richness.

Keywords:
Class incremental learningEffective rankFeature richness

More Related Videos

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

Related Experiment Videos

Last Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Class Incremental Learning (CIL) enables models to learn sequentially without forgetting past knowledge.
  • Existing CIL methods primarily focus on backward compatibility, risking performance on new tasks.
  • Forward compatibility methods are emerging to improve performance on unseen tasks.

Purpose of the Study:

  • To introduce an effective method, Feature Richness enhancement (RFR), to improve forward compatibility in CIL.
  • To enhance the model's ability to learn new tasks without compromising previously acquired knowledge.
  • To achieve dual objectives of backward and forward compatibility in continual learning.

Main Methods:

  • The proposed RFR method increases the effective rank of representations during the base learning session.
  • A theoretical link between effective rank and Shannon entropy of representations is established.
  • RFR was integrated and tested with eleven established CIL methods.

Main Results:

  • RFR effectively enhances performance on novel tasks.
  • The method demonstrates significant mitigation of catastrophic forgetting.
  • Average incremental accuracy improved across all eleven tested CIL methods.

Conclusions:

  • The RFR method offers a robust approach to improving forward compatibility in CIL.
  • RFR successfully balances learning new information with retaining old knowledge.
  • This enhancement leads to superior overall performance in continual learning scenarios.