论文部分内容阅读
首先给出了用神经网络求解四色图着色问题的神经网络结构和能量函数 ,然后采用了具有瞬态混沌特性的神经网络 ( TCNN)来解四色图着色问题 .由于引入具有复杂动态特性的瞬态混沌使得该法具有很强的搜索全局最优解的能力 .仿真结果表明 ,用该法解四色图着色问题总能保证使能量函数收敛到最优解 ,有效避免了用传统的 Hopfield人工神经网络 ( HNN)解此问题时极易陷入局部极小的缺陷 ,并且收敛速度更快 .另外我们还用此法求解了属于 NP-完全问题的 K色图着色问题
Firstly, neural network structure and energy function for solving four-color image coloring problem using neural network are given, and then the neural network (TCNN) with transient chaos characteristics is used to solve the coloring problem of four-color image. Due to the introduction of complex dynamic characteristics The transient chaos makes the method have a strong ability to search the global optimal solution.The simulation results show that this method can always guarantee that the energy function converges to the optimal solution and effectively avoids using the traditional Hopfield Artificial neural network (HNN) can easily get into local minima and solve more quickly when solving this problem.In addition, we also use this method to solve the coloring problem of K-color map which belongs to NP-complete problem