Scientists apply the principles of the brain nervous system to brain-like pulsed neural networks

, Zeng Yi, a researcher at the Brain Intelligence Research Center of the Institute of Automation of the Chinese Academy of Sciences, summarized seven brain-inspired learning guidelines in a study that was successfully applied to improving pulsed neural networks. By combining different brain-inspired rules, experimental studies have verified that deep pulsed neural networks can get better and better classification performance with the introduction of more and more carefully selected, brain-inspired rules. The results were published
.
compared with traditional artificial neurons, pulsed neurons already have a more solid biological authenticity, but the traditional pulsed neural network model only captures the initial local learning training rules in the process of brain information processing. The seven learning principles proposed by the research team are derived from the experimental study of the biological brain, and each reflects the learning characteristics of the biological network from different sides, such as the dynamic distribution of neurons, the adaptive growth and extinction mechanism of synapses, different synhap plasticity learning mechanisms (such as different types of timing dependent on synhap plasticity), the regulation mechanism of network background noise on learning, the proportion of excitable and inhibitory neurons to the adjustment mechanism of learning.
these learning principles, the dynamic distribution of neurons, the generation and extinction of synapses, plastic models and so on are considered to be important characteristics of brain neural network processing information. The team introduced these brain-inspired rules into the pulsed neural network model.
researchers say their proposed model is characterized by a more bio-explanatory computer than traditional neural network models, in which case understanding the meaning of brain information processing mechanisms and processes through computational modeling, and the resulting inspiration, is far greater than the pursuit of performance. (Source: Science Network Pengkefeng)