On the Computational Complexities of Complex-valued Neural Networks
This work addresses the need for computational complexity analysis in CVNNs to guide algorithm selection for low-power digital signal processing applications, but it is incremental as it builds on existing studies.
The paper analyzes the computational complexities of complex-valued neural networks (CVNNs), providing both quantitative and asymptotic measures to estimate floating-point operations, which is crucial for implementing them in low-power systems.
Complex-valued neural networks (CVNNs) are nonlinear filters used in the digital signal processing of complex-domain data. Compared with real-valued neural networks~(RVNNs), CVNNs can directly handle complex-valued input and output signals due to their complex domain parameters and activation functions. With the trend toward low-power systems, computational complexity analysis has become essential for measuring an algorithm's power consumption. Therefore, this paper presents both the quantitative and asymptotic computational complexities of CVNNs. This is a crucial tool in deciding which algorithm to implement. The mathematical operations are described in terms of the number of real-valued multiplications, as these are the most demanding operations. To determine which CVNN can be implemented in a low-power system, quantitative computational complexities can be used to accurately estimate the number of floating-point operations. We have also investigated the computational complexities of CVNNs discussed in some studies presented in the literature.