A New Activation Function in the Hop eld Network for Solving Optimization Problems
نویسندگان
چکیده
This paper shows that the performance of the Hoppeld network for solving optimization problems can be improved by using a new activation (output) function. The eeects of the activation function on the performance of the Hoppeld network are analyzed. It is shown that the sigmoid activation function in the Hoppeld network is sensitive to noise of neurons. The reason is that the sigmoid function is most sensitive in the range where noise is most predominant. A new activation function that is more robust against noise is proposed. The new activation function has the capability of amplifying the signals between neurons while suppressing noise. The performance of the new activation function is evaluated through simulation. Compared with the sigmoid function , the new activation function reduces the error rate of tour length by 30.6% and increases the percentage of valid tours by 38.6% during simulation on 200 randomly generated city distributions of the 10-city traveling salesman problem.
منابع مشابه
Improving the Performance of the Hopfield Network for Solving Optimization Problems
IMPROVING THE PERFORMANCE OF THE HOPFIELD NETWORK FOR SOLVING OPTIMIZATION PROBLEMS Xinchuan Zeng Department of Computer Science Master of Science Three approaches that signi cantly improve the performance of the Hop eld network for solving optimization problems have been developed and evaluated in this work. The rst approach uses a new activation function to reduce the e ects of noise in the n...
متن کاملCompetitive neural network to solve scheduling problems
Most scheduling problems have been demonstrated to be NP-complete problems. The Hop"eld neural network is commonly applied to obtain an optimal solution in various di!erent scheduling applications, such as the traveling salesman problem (TSP), a typical discrete combinatorial problem. Hop"eld neural networks, although providing rapid convergence to the solution, require extensive e!ort to deter...
متن کاملHop eld Networks for Solving Tower of Hanoi Problem
In this paper, Hop eld neural networks have been considered in solving tower of Hanoi test which is used in determining of de cit of planning capability of human prefrontal cortex. The main di erence of this work from the ones in the literature which use neural networks, is: The tower of Hanoi problem has been formulated here as a special shortest path problem. In the literature, some Hop eld n...
متن کاملExtending the power and capacity of constraint satisfaction networks
This work focuses on improving the Hop eld network for solv ing optimization problems Although much work has been done in this area the performance of the Hop eld network is still not satisfactory in terms of valid convergence and quality of solutions We address this issue in this work by combing a new activation function EBA and a new relax ation procedure CR in order to improve the performanc...
متن کاملAn Efficient Neurodynamic Scheme for Solving a Class of Nonconvex Nonlinear Optimization Problems
By p-power (or partial p-power) transformation, the Lagrangian function in nonconvex optimization problem becomes locally convex. In this paper, we present a neural network based on an NCP function for solving the nonconvex optimization problem. An important feature of this neural network is the one-to-one correspondence between its equilibria and KKT points of the nonconvex optimizatio...
متن کامل