DeepAI AI Chat
Log In Sign Up

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

by   Yihong Dong, et al.
Tongji University
Carnegie Mellon University

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.


Invariant Meta Learning for Out-of-Distribution Generalization

Modern deep learning techniques have illustrated their excellent capabil...

Meta-Learning with Temporal Convolutions

Deep neural networks excel in regimes with large amounts of data, but te...

Meta-Learning for Few-Shot Time Series Classification

Deep neural networks (DNNs) have achieved state-of-the-art results on ti...

Complex Transformer: A Framework for Modeling Complex-Valued Sequence

While deep learning has received a surge of interest in a variety of fie...

Meta-Learning with Hessian Free Approach in Deep Neural Nets Training

Meta-learning is a promising method to achieve efficient training method...

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

Deep neural networks are highly effective when a large number of labeled...

Faster Meta Update Strategy for Noise-Robust Deep Learning

It has been shown that deep neural networks are prone to overfitting on ...