Kulkarni Raghavendra V, Venayagamoorthy Ganesh K
Real-Time Power and Intelligent Systems Laboratory, Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA.
Neural Netw. 2009 Sep;22(7):1011-7. doi: 10.1016/j.neunet.2009.07.027. Epub 2009 Jul 25.
Feedforward neural networks such as multilayer perceptrons (MLP) and recurrent neural networks are widely used for pattern classification, nonlinear function approximation, density estimation and time series prediction. A large number of neurons are usually required to perform these tasks accurately, which makes the MLPs less attractive for computational implementations on resource constrained hardware platforms. This paper highlights the benefits of feedforward and recurrent forms of a compact neural architecture called generalized neuron (GN). This paper demonstrates that GN and recurrent GN (RGN) can perform good classification, nonlinear function approximation, density estimation and chaotic time series prediction. Due to two aggregation functions and two activation functions, GN exhibits resilience to the nonlinearities of complex problems. Particle swarm optimization (PSO) is proposed as the training algorithm for GN and RGN. Due to a small number of trainable parameters, GN and RGN require less memory and computational resources. Thus, these structures are attractive choices for fast implementations on resource constrained hardware platforms.
前馈神经网络，如多层感知器（MLP）和递归神经网络，被广泛用于模式分类、非线性函数逼近、密度估计和时间序列预测。通常需要大量神经元才能准确执行这些任务，这使得多层感知器在资源受限的硬件平台上进行计算实现时吸引力降低。本文强调了一种称为广义神经元（GN）的紧凑型神经架构的前馈和递归形式的优点。本文表明，广义神经元和递归广义神经元（RGN）可以进行良好的分类、非线性函数逼近、密度估计和混沌时间序列预测。由于具有两个聚合函数和两个激活函数，广义神经元对复杂问题的非线性具有弹性。粒子群优化（PSO）被提议作为广义神经元和递归广义神经元的训练算法。由于可训练参数数量少，广义神经元和递归广义神经元需要更少的内存和计算资源。因此，这些结构是在资源受限的硬件平台上进行快速实现的有吸引力的选择。
