Block-based neural networks
Block-based neural networks
复制标题
基于块的神经网络
DOI：
10.1109/72.914525
复制
发表时间：
2001
影响因子：
--
通讯作者：
S. Kong
中科院分区：
文献类型：
--
作者：
S. Moon;S. Kong
本文介绍了一种新型的基于块的神经网络（BBNN）模型及其基于遗传算法的结构和权重的优化。 BBNN的架构由一个2D阵列组成，具有四个可变输入/输出节点和连接权重的基本块。每个块可以根据结构设置具有四种不同的内部配置之一，BBNN模型包括一些限制，例如2D阵列和整数权重，以便使用可重新配置的硬件（例如可编程可编程逻辑阵列（FPGA））更轻松地实现。 BBNN的结构和权重编码与对应于FPGA的配置位相对应的位字符串。使用具有2D编码和修改的遗传运算符的遗传算法在全球范围内对配置位进行优化。模拟表明，优化的BBNN可以解决工程问题，例如模式分类和移动机器人控制。
This paper presents a novel block-based neural network (BBNN) model and the optimization of its structure and weights based on a genetic algorithm. The architecture of the BBNN consists of a 2D array of fundamental blocks with four variable input/output nodes and connection weights. Each block can have one of four different internal configurations depending on the structure settings, The BBNN model includes some restrictions such as 2D array and integer weights in order to allow easier implementation with reconfigurable hardware such as field programmable logic arrays (FPGA). The structure and weights of the BBNN are encoded with bit strings which correspond to the configuration bits of FPGA. The configuration bits are optimized globally using a genetic algorithm with 2D encoding and modified genetic operators. Simulations show that the optimized BBNN can solve engineering problems such as pattern classification and mobile robot control.