方法证据记录
Online Few-shot Learning
Online Few-shot Learning combines the streaming update principle of online learning with the data-efficiency goal of few-shot learning, enabling a model to continuously adapt to new tasks or classes from only a handful of labeled examples as data arrives sequentially — without access to the full historical dataset.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Online Few-shot Learning (Streaming Meta-Learning from Scarce Labels)
分类方法记录 · ml-model / machine-learning
- Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930. · URL
- Javed, K., & White, M. (2019). Meta-Learning Representations for Continual Learning. Advances in Neural Information Processing Systems (NeurIPS), 32. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。