Version 1
: Received: 24 December 2023 / Approved: 27 December 2023 / Online: 27 December 2023 (04:19:26 CET)
How to cite:
Nokhwal, S.; Kumar, N.; G. Shiva, S. Investigating the Terrain of Class-incremental Continual Learning: A Brief Survey. Preprints2023, 2023122052. https://doi.org/10.20944/preprints202312.2052.v1
Nokhwal, S.; Kumar, N.; G. Shiva, S. Investigating the Terrain of Class-incremental Continual Learning: A Brief Survey. Preprints 2023, 2023122052. https://doi.org/10.20944/preprints202312.2052.v1
Nokhwal, S.; Kumar, N.; G. Shiva, S. Investigating the Terrain of Class-incremental Continual Learning: A Brief Survey. Preprints2023, 2023122052. https://doi.org/10.20944/preprints202312.2052.v1
APA Style
Nokhwal, S., Kumar, N., & G. Shiva, S. (2023). Investigating the Terrain of Class-incremental Continual Learning: A Brief Survey. Preprints. https://doi.org/10.20944/preprints202312.2052.v1
Chicago/Turabian Style
Nokhwal, S., Nirman Kumar and Sajjan G. Shiva. 2023 "Investigating the Terrain of Class-incremental Continual Learning: A Brief Survey" Preprints. https://doi.org/10.20944/preprints202312.2052.v1
Abstract
Continual learning, a crucial facet of machine learning, involves the perpetual acquisition of valuable insights from incoming data, sans the necessity for full dataset access. Esteemed as a fundamental goal in artificial intelligence, continual learning grapples with an enduring challenge—catastrophic forgetting. A proficient model must exhibit adaptability for new data assimilation and robustness to retain existing knowledge. Class-incremental learning (CIL) aids the gradual integration of knowledge from newly introduced classes, forming a universal classifier. However, directly training the model with fresh class instances triggers a problem—forgetting distinguishing features of prior classes, causing a performance decline. Addressing such issues in machine learning, this survey aims to delineate significant challenges, outcomes, and recent advancements, including our contributions to CIL techniques, especially in image classification.
Keywords
Continual learning; Class-incremental learning; Incremental learning; Lifelong learning; Learning on the fly; Online learning; Dynamic learning; Learning with limited data; Adaptive learning; Sequential learning; Learning from streaming data; Learning from non-stationary distributions; Never-ending learning; Learning without forgetting; Catastrophic forgetting; Memory-aware learning
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.