arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04392cs.LGcs.AIeess.SP
收藏

信号Transformer:复值注意和元学习在信号识别中的应用

Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition

Tongji University(同济大学);Carnegie Mellon University(卡内基梅隆大学);IBM Thomas J. Watson Research Center(IBM托马斯·J·沃森研究中心)

Yihong Dong, Ying Peng, Muqiao Yang, Songtao Lu, Qingjiang Shi

摘要:

近年来,深度神经网络已被证明是解决信号识别问题的一类有用工具,特别是用于识别信号的非线性特征结构。然而,大多数深度学习技术的这种能力在很大程度上依赖于大量的训练数据,因此当训练数据样本的数量很小或在测试阶段出现看不见的数据时,经典神经网络的性能会急剧下降。这需要一个先进的战略,即,与模型无关的元学习(MAML),其能够捕获数据样本或信号的不变表示。本文受信号特殊结构的启发,针对实际时间序列信号中包含的实部和虚部,提出了一种利用复数域中的注意力和元学习来解决Few-Shot信号识别问题的复值注意力Meta学习器(CAMEL)。据我们所知,这也是第一个复值MAML,可以找到一般非凸问题的理论收敛保证的一阶稳定点。大量的实验结果表明,所提出的CAMEL相比,国家的最先进的方法的优越性。

英文摘要:

Deep neural networks have been shown as a class of useful tools for addressing signal recognition issues in recent years, especially for identifying the nonlinear feature structures of signals. However, this power of most deep learning techniques heavily relies on an abundant amount of training data, so the performance of classic neural nets decreases sharply when the number of training data samples is small or unseen data are presented in the testing phase. This calls for an advanced strategy, i.e., model-agnostic meta-learning (MAML), which is able to capture the invariant representation of the data samples or signals. In this paper, inspired by the special structure of the signal, i.e., real and imaginary parts consisted in practical time-series signals, we propose a Complex-valued Attentional MEta Learner (CAMEL) for the problem of few-shot signal recognition by leveraging attention and meta-learning in the complex domain. To the best of our knowledge, this is also the first complex-valued MAML that can find the first-order stationary points of general nonconvex problems with theoretical convergence guarantees. Extensive experiments results showcase the superiority of the proposed CAMEL compared with the state-of-the-art methods.

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。

↑