Research on Compound Numerical Spiking Neural P Systems
Meng Hu, Xiantai Gou, Fang Deng, Qifen Liu and Haina Rong
The Spiking Neural P Systems (SNP) is a neural computing model inspired by the mechanism of biological neurons transmitting information. It has received extensive attention from scholars due to its powerful computing power and brain-like information transmission mode. Its application potential is huge, but in the field of pattern recognition it has not been completely solved. This paper introduces the Markov decision-making process, draws on the Q-Learning in reinforcement learning, designing a compound Numerical Spiking Neural P Systems (NSNP) with multiple production functions. This learning model has the ability to learn selection rules and strategies. Through the NP-Complete problem and the IRIS dataset species identification, the effectiveness of the algorithm in the discrete state and the continuous state is verified respectively. Experimental results show that the recognition accuracy is close to 100%. The model has the ability to solve nonlinear model recognition problems, and the single neuron has a strong computing power. Compared with the traditional CNN network, it uses fewer neurons and has a certain development potential.
Keywords: Membrane computing, Numerical Spike neural P systems, image recognition, STDP learning ability