Going beyond xai: A systematic survey for explanation-guided learning
As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing
DNNs become more complex and diverse, ranging from improving a conventional model …
DNNs become more complex and diverse, ranging from improving a conventional model …
CeCR: Cross-entropy contrastive replay for online class-incremental continual learning
G Sun, B Ji, L Liang, M Chen - Neural Networks, 2024 - Elsevier
Aiming at the realization of learning continually from an online data stream, replay-based
methods have shown superior potential. The main challenge of replay-based methods is the …
methods have shown superior potential. The main challenge of replay-based methods is the …
Neural networks special issue on Artificial Intelligence and brain science
Neural Networks special issue on Artificial Intelligence and Brain Science | Neural Networks
skip to main content ACM Digital Library home ACM home Google, Inc. (search) Advanced …
skip to main content ACM Digital Library home ACM home Google, Inc. (search) Advanced …
A robust and anti-forgettiable model for class-incremental learning
J Chen, Y Xiang - Applied Intelligence, 2023 - Springer
In many real-world scenarios, neural network models are not always fixed; they are
expected to adapt to a dynamic environment and incrementally learn new knowledge …
expected to adapt to a dynamic environment and incrementally learn new knowledge …
On Representation-Level Forgetting in Class Incremental Learning: What's the Bottleneck?
Although the concept of Catastrophic Forgetting (CF) is straightforward in Class Incremental
Learning (CIL), the causes of CF in models are still vague. In this paper, by introducing the …
Learning (CIL), the causes of CF in models are still vague. In this paper, by introducing the …