Fast Complex Adaptive Spline Neural Networks for Digital Signal Processing

, In this paper, we study the complex-domain arttficial neural networks called adaptive spline neural networks (ASNN), deflned in the complex domain, which are able to adapt their activation functions by varying the control points of a Catmull-Rom cubic spline. This kind of neural network can be implemented as a very simple structure able to improve the generalization capabilities using few training epochs. Due to its low architectural complexity this network can be used to cope with several nonlinear DSP problems at high sampling rate. In particular, we investigate the application of this new neural network model to the adaptive channel equalization problem. The goal is to design a receiver which compensates the HPA nonlinearities in digital radio links and performs the symbols extraction from the received data (demodulation process), when a 16-QA.M is used.