Guarnieri S, Piazza F, Uncini A
Dipartimento di Elettronica e Automatica, Università di Ancona, Italy, 60131 Ancona, Italy.
IEEE Trans Neural Netw. 1999;10(3):672-83. doi: 10.1109/72.761726.
In this paper, a new adaptive spline activation function neural network (ASNN) is presented. Due to the ASNN's high representation capabilities, networks with a small number of interconnections can be trained to solve both pattern recognition and data processing real-time problems. The main idea is to use a Catmull-Rom cubic spline as the neuron's activation function, which ensures a simple structure suitable for both software and hardware implementation. Experimental results demonstrate improvements in terms of generalization capability and of learning speed in both pattern recognition and data processing tasks.
本文提出了一种新型自适应样条激活函数神经网络（ASNN）。由于ASNN具有高表示能力，因此可以训练具有少量互连的网络来实时解决模式识别和数据处理问题。主要思想是使用Catmull-Rom三次样条作为神经元的激活函数，这确保了适合软件和硬件实现的简单结构。实验结果表明，在模式识别和数据处理任务中，泛化能力和学习速度都有所提高。
