A New Learning Paradigm for Stochastic Configuration Network: SCN+
Yanshuang Ao, Xinyu Zhou, Wei Dai
2022-03-11Incremental Learning
Abstract
Learning using privileged information (LUPI) paradigm, which pioneered teacher-student interaction mechanism, makes the learning models use additional information in training stage. This paper is the first to propose an incremental learning algorithm with LUPI paradigm for stochastic configuration network (SCN), named SCN+. This novel algorithm can leverage privileged information into SCN in the training stage, which provides a new method to train SCN. Moreover, the convergences have been studied in this paper. Finally, experimental results indicate that SCN+ indeed performs favorably.
Related Papers
The Bayesian Approach to Continual Learning: An Overview2025-07-11Balancing the Past and Present: A Coordinated Replay Framework for Federated Class-Incremental Learning2025-07-10Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts2025-07-09DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic2025-06-26Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation2025-06-12Hyperbolic Dual Feature Augmentation for Open-Environment2025-06-10L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning2025-06-01CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning2025-05-30