元学习(计算机科学)
计算机科学
人工智能
一般化
机器学习
推论
超参数
架空(工程)
人工神经网络
趋同(经济学)
深度学习
任务(项目管理)
工程类
数学分析
系统工程
经济
操作系统
经济增长
数学
作者
Antreas Antoniou,Harrison Edwards,Amos Storkey
出处
期刊:Cornell University - arXiv
日期:2018-10-22
被引量:135
摘要
The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAML, which we call MAML++.
科研通智能强力驱动
Strongly Powered by AbleSci AI