MAC：一种用于特征学习与重组的元学习方法
MAC: A Meta-Learning Approach for Feature Learning and Recombination
AI总结：
本文提出MAC方法，通过增加网络宽度和额外计算单元，在元测试时学习新特征并与现有特征重组，在非相似任务分布上比ANIL提升约13%。
摘要：
基于优化的元学习旨在学习一个初始化，使得一个新的未见任务能够在几次梯度更新内被学习。模型无关元学习（MAML）是一个包含两个优化循环的基准算法。内循环专门用于学习新任务，外循环则导致元初始化。然而，ANIL（几乎无内循环）算法表明，特征重用是MAML中快速学习的替代方案。因此，元初始化阶段使MAML为特征重用做好准备，并消除了快速学习的需要。与ANIL相反，我们假设在元测试期间可能需要学习新特征。来自非相似分布的新未见任务将需要快速学习，以及现有特征的重用和重组。在本文中，我们引用了神经网络的宽度-深度对偶性，其中我们通过添加额外计算单元（ACU）来增加网络的宽度。ACU使得在元测试任务中能够学习新的原子特征，并且相关的宽度增加促进了前向传播中的信息传播。新学习的特征在最后一层与现有特征结合以进行元学习。实验结果表明，我们提出的MAC方法在非相似任务分布上比现有ANIL算法表现优越约13%（5-shot任务设置）。
英文摘要：
Optimization-based meta-learning aims to learn an initialization so that a new unseen task can be learned within a few gradient updates. Model Agnostic Meta-Learning (MAML) is a benchmark algorithm comprising two optimization loops. The inner loop is dedicated to learning a new task and the outer loop leads to meta-initialization. However, ANIL (almost no inner loop) algorithm shows that feature reuse is an alternative to rapid learning in MAML. Thus, the meta-initialization phase makes MAML primed for feature reuse and obviates the need for rapid learning. Contrary to ANIL, we hypothesize that there may be a need to learn new features during meta-testing. A new unseen task from non-similar distribution would necessitate rapid learning in addition reuse and recombination of existing features. In this paper, we invoke the width-depth duality of neural networks, wherein, we increase the width of the network by adding extra computational units (ACU). The ACUs enable the learning of new atomic features in the meta-testing task, and the associated increased width facilitates information propagation in the forwarding pass. The newly learnt features combine with existing features in the last layer for meta-learning. Experimental results show that our proposed MAC method outperformed existing ANIL algorithm for non-similar task distribution by approximately 13% (5-shot task setting)
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
