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
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 2 
Figure 3
Abstract
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...