Continual learning for recurrent neural networks: an empirical evaluation
Learning continuously during all model lifetime is fundamental to deploy machine learning
solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with …
solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with …
Few-shot continual learning for audio classification
Supervised learning for audio classification typically imposes a fixed class vocabulary,
which can be limiting for real-world applications where the target class vocabulary is not …
which can be limiting for real-world applications where the target class vocabulary is not …
Few-shot class-incremental audio classification using dynamically expanded classifier with self-attention modified prototypes
Most existing methods for audio classification assume that the vocabulary of audio classes
to be classified is fixed. When novel (unseen) audio classes appear, audio classification …
to be classified is fixed. When novel (unseen) audio classes appear, audio classification …
[HTML][HTML] Task-agnostic continual reinforcement learning: In praise of a simple baseline
We study task-agnostic continual reinforcement learning (TACRL) in which standard RL
challenges are compounded with partial observability stemming from task agnosticism, as …
challenges are compounded with partial observability stemming from task agnosticism, as …
Learning representations for new sound classes with continual self-supervised learning
In this article, we work on a sound recognition system that continually incorporates new
sound classes. Our main goal is to develop a framework where the model can be updated …
sound classes. Our main goal is to develop a framework where the model can be updated …
Class-incremental learning for time series: Benchmark and evaluation
Z Qiao, Q Pham, Z Cao, HH Le, PN Suganthan… - arXiv preprint arXiv …, 2024 - arxiv.org
Real-world environments are inherently non-stationary, frequently introducing new classes
over time. This is especially common in time series classification, such as the emergence of …
over time. This is especially common in time series classification, such as the emergence of …
Few-shot class-incremental audio classification using stochastic classifier
It is generally assumed that number of classes is fixed in current audio classification
methods, and the model can recognize pregiven classes only. When new classes emerge …
methods, and the model can recognize pregiven classes only. When new classes emerge …
Incremental learning BiLSTM based on dynamic proportional adjustment mechanism and experience replay for quantitative detection of blade crack propagation
J Shen, T Ma, D Song, F Xu - Structural Health Monitoring, 2024 - journals.sagepub.com
In the traditional quantitative detection model for blade cracks in centrifugal fan, it is
assumed that the data distribution is fixed or stable. However, the new data brought by the …
assumed that the data distribution is fixed or stable. However, the new data brought by the …
Continual learning for on-device environmental sound classification
Continuously learning new classes without catastrophic forgetting is a challenging problem
for on-device environmental sound classification given the restrictions on computation …
for on-device environmental sound classification given the restrictions on computation …
Task-agnostic continual reinforcement learning: Gaining insights and overcoming challenges
Continual learning (CL) enables the development of models and agents that learn from a
sequence of tasks while addressing the limitations of standard deep learning approaches …
sequence of tasks while addressing the limitations of standard deep learning approaches …