Hybrid particle swarm pulse neural network mapping method for power consumption

A pulse neural network and hybrid particle swarm technology, applied in biological neural network models, neural architecture, genetic rules, etc., can solve the problems of slow execution speed, poor scalability, high power consumption, etc., to reduce system power consumption and enhance applications property, overcoming the effect of premature convergence

CN107169561AInactive Publication Date: 2017-09-15GUANGXI NORMAL UNIV
3 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2017-09-15
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a hybrid particle swarm pulse neural network mapping method for power consumption. On the basis of a neuron node mapping way with combination of a particle swarm algorithm and a genetic algorithm, an optimal mapping result of mapping of a neuron node to a hardware system is obtained. The mapping method employs the particle swarm algorithm; the mutation operation of the genetic algorithm is combined during the particle swarm algorithm operation process and thus the basic particle swarm algorithm is improved; and the algorithm is circulated until a terminal condition is met. Therefore, defects of performances of the basic particle swarm algorithm can be overcome and the original searching capability of the particle swarm algorithm is utilized completely; a defect that the basic particle swarm algorithm is convergent too early and thus is easy to fall into local optimal node can be overcome; and thus the algorithm can search a global optimal solution. And thus the power consumption of the system can be reduced and the applicability of the mapping plan can be enhanced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of intelligent optimization, in particular to a power consumption-oriented hybrid particle swarm impulse neural network mapping method. Background technique

[0002] The research of Spiking Neuron Networks (SNN) has increasingly become a research hotspot in the field of computational intelligence. The spiking neural network adopts a coding method based on time spike sequences, which is closer to the understanding of the biological nervous system in brain science. Compared with the traditional neural network, the spiking neural network shows stronger bionic characteristics and computing power.

[0003] As the most biologically realistic artificial neural network model so far, all neurons of the spiking neural network have a potential pulse trigger mechanism similar to that of biological neurons. This mechanism makes the spiking neural network different from the traditional artificial neural network based on pulse freq...

Examples

Embodiment

[0048] Such as Figure 2 to Figure 4 As shown, a power-consumption-oriented hybrid particle swarm pulse neural network mapping method, through the combination of particle swarm algorithm and genetic algorithm for neuron node mapping, the best mapping result of neuron node mapping to the hardware system is obtained, The main body of the mapping method adopts the particle swarm optimization algorithm. During the operation of the particle swarm optimization algorithm, the mutation operation of the genetic algorithm is combined to improve the basic particle swarm optimization algorithm. The algorithm is cyclic until the termination condition is met, including the following steps:

[0049] The first step: initialization: set the number of particles in the particle swarm N p , maximum number of iterations I, mutation threshold T m , randomly generate the initial particle group according to the particle representation, and the representation of each particle is x=(x 1 , x 2 , x 3...