Design and Analysis of Positively Self-Feedbacked Hopfield Neural Network for Crossbar Switching
نویسندگان
چکیده
After the original work of Hopfield and Tank, a lot of modified Hopfield neural network models have been proposed for combinatorial optimization problems. Recently, a positively selffeedbacked Hopfield neural network architecture was proposed by Li et al. and successfully applied to crossbar switching problem. In this paper, we analysis the dynamics of the positively self-feedbacked Hopfield neural network, then show the role of the self-feedback and point out where the good performance comes from. Based on the theoretical analysis, we get better simulation results for crossbar switching problem by selecting suitably positive self-feedback value of the network.
منابع مشابه
A New Algorithm for Crossbar Switch Problem Using Hopfield Neural Network with Continuous Hysteresis Neurons
In this paper, we propose a continuous hysteresis neurons Hopfield neural network architecture for efficiently solving crossbar switch problems. A Hopfield neural network architecture with continuous hysteresis and its collective computational properties are studied. It is proved theoretically and confirmed by simulating the randomly generated Hopfield neural network with continuous hysteresis ...
متن کاملCrossbar Switch Problem Solver by Hysteresis Neural Networks
In this paper, we propose a continuous hysteresis neurons (CHN) Hopfield neural network architecture for efficiently solving crossbar switch problems. A Hopfield neural network architecture with continuous hysteresis and its collective computational properties are studied. It is proved theoretically and confirmed by simulating the randomly generated Hopfield neural network with CHN. The network...
متن کاملNeural Network Modelling of Optimal Robot Movement Using Branch and Bound Tree
In this paper a discrete competitive neural network is introduced to calculate the optimal robot arm movements for processing a considered commitment of tasks, using the branch and bound methodology. A special method based on the branch and bound methodology, modified with a travelling path for adapting in the neural network, is introduced. The main neural network of the system consists of diff...
متن کاملNeuro-Optimizer: A New Artificial Intelligent Optimization Tool and Its Application for Robot Optimal Controller Design
The main objective of this paper is to introduce a new intelligent optimization technique that uses a predictioncorrectionstrategy supported by a recurrent neural network for finding a near optimal solution of a givenobjective function. Recently there have been attempts for using artificial neural networks (ANNs) in optimizationproblems and some types of ANNs such as Hopfield network and Boltzm...
متن کاملPattern Classification by Memristive Crossbar Circuits with Ex-situ and In-situ Training
The development of artificial neural networks (ANNs) based on emerging non-volatile memory, such as metal oxide memristors, has attracted an increasing interest recently. In the simplest form of such ANNs, the neurons are implemented with conventional (complementary metal-oxide-semiconductor) technology and interconnected by memristors functioning as artificial synapses. We will first introduce...
متن کامل