Optimised Continually Evolved Classifier for Few-Shot Learning Overcoming Catastrophic Forgetting

Rupatai Lichode and Swapnili Karmore
Additional contact information
Rupatai Lichode: Department of Computer Science and Engineering, G H Raisoni University, Saikheda, Borgaon, Madhya Pradesh 480337, India
Swapnili Karmore: Department of Computer Science and Engineering, G H Raisoni University, Saikheda, Borgaon, Madhya Pradesh 480337, India

Journal of Information & Knowledge Management (JIKM), 2025, vol. 24, issue 02, 1-24

Abstract: Catastrophic forgetting (CF) poses the most important challenge in neural networks for continual learning. During training, numerous current approaches replay precedent data that deviate from the constraints of an optimal continual learning system. In this work, optimisation-enabled continually evolved classifier is used for the CF. Moreover, a few-shot continual learning model is exploited to mitigate CF. Initially, images undergo pre-processing using Contrast Limited Adaptive Histogram Equalisation (CLAHE). Then; the pre-processed outputs are utilised in the classification through Continually Evolved Classifiers based on few-shot incremental learning. Here, the initial training is done by using the CNN (Convolutional Neural Network) model and then the pseudo incremental learning phase is performed. Furthermore, to enhance the performance, an optimisation approach, called Serial Exponential Sand Cat Swarm Optimisation (SExpSCSO), is developed. SExpSCSO algorithm modifies Sand Cat Swarm Optimisation by incorporating the serial exponential weighted moving average concept. The proposed SExpSCSO is applied to train the continually evolved classifier by optimising weights and thus, improves the classifiers performance. Finally, the experimentation analysis reveals that the adopted system acquired the maximal accuracy of 0.677, maximal specificity of 0.592, maximal precision of 0.638, recall of 0.716 and F-measure of 0.675.

Keywords: Catastrophic forgetting; few shot; learning; classifier; CNN; optimisation algorithm (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219649225500078
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:jikmxx:v:24:y:2025:i:02:n:s0219649225500078

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219649225500078

Access Statistics for this article

Journal of Information & Knowledge Management (JIKM) is currently edited by Professor Suliman Hawamdeh

More articles in Journal of Information & Knowledge Management (JIKM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().