Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared
to their real counter-parts in speech enhancement, image and signal processing …

The increasing complexity and dynamical property in stock markets are key challenges of
the financial industry, in which inflexible trading strategies designed by experienced …

A single dendritic neuron model (DNM) that owns the nonlinear information processing
ability of dendrites has been widely used for classification and prediction. Complex-valued …

We generalize the classical universal approximation theorem for neural networks to the case
of complex-valued neural networks. Precisely, we consider feedforward networks with a …

Ultrasound imaging is widely used in medical diagnosis. It has the advantages of being
performed in real time, cost-efficient, noninvasive, and nonionizing. The traditional delay …

The main challenge of cross-modal matching is to construct a shared subspace reflecting
semantic closeness. Asymmetric relevance, especially the one-to-many matching case …

This paper proposes a set of rules to revise various neural networks for 3D point cloud
processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when …

Sequence models based on linear state spaces (SSMs) have recently emerged as a
promising choice of architecture for modeling long range dependencies across various …

Multi-scale information is crucial for modeling time series. Although most existing methods
consider multiple scales in the time-series data, they assume all kinds of scales are equally …

Adaptive filtering algorithms are pervasive throughout signal processing and have had a
material impact on a wide variety of domains including audio processing …