Limits...
A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH
The convergence performance of the memristive neural network under different P. (a) The relationship between iteration and rewiring probability. (b) The effective approximation number in 50 times simulations under varying rewiring probability.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4150482&req=5

fig13: The convergence performance of the memristive neural network under different P. (a) The relationship between iteration and rewiring probability. (b) The effective approximation number in 50 times simulations under varying rewiring probability.

Mentions: In order to verify the superior performance of the memristive small-world neuronal networks and figure out the optimal structure, we conducted a series of simulations to observe the convergence performance of the proposed network under different P. Figure 13(a) shows the approximation speed (iteration times) of different network structures, that is, the smallest iteration number for reaching the predefined approximation error ɛ = 0.0001. Each drawn point is the average value of 50 times runs. It can be observed that the small-world networks (0 < P < 1) need much less iteration times than the regular neural network (when P = 0), which demonstrates its advantage in processing speed. Furthermore, when P = 0.08, the network has the fast approximation speed.


A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

The convergence performance of the memristive neural network under different P. (a) The relationship between iteration and rewiring probability. (b) The effective approximation number in 50 times simulations under varying rewiring probability.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4150482&req=5

fig13: The convergence performance of the memristive neural network under different P. (a) The relationship between iteration and rewiring probability. (b) The effective approximation number in 50 times simulations under varying rewiring probability.
Mentions: In order to verify the superior performance of the memristive small-world neuronal networks and figure out the optimal structure, we conducted a series of simulations to observe the convergence performance of the proposed network under different P. Figure 13(a) shows the approximation speed (iteration times) of different network structures, that is, the smallest iteration number for reaching the predefined approximation error ɛ = 0.0001. Each drawn point is the average value of 50 times runs. It can be observed that the small-world networks (0 < P < 1) need much less iteration times than the regular neural network (when P = 0), which demonstrates its advantage in processing speed. Furthermore, when P = 0.08, the network has the fast approximation speed.

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH