RESUMO
Under the current situation of the rapid development of brain-like artificial intelligence and the increasingly complex electromagnetic environment, the most bionic and anti-interference spiking neural network has shown great potential in computing speed, real-time information processing, and spatiotemporal data processing. Spiking neural network is the core part of brain-like artificial intelligence, which realizes brain-like computing by simulating the structure of biological neural network and the way of information transmission. This article first summarizes the advantages and disadvantages of the five models, and analyzes the characteristics of several network topologies. Then, it summarizes the spiking neural network algorithms. The unsupervised learning based on spike timing dependent plasticity (STDP) rules and four types of supervised learning algorithms are analyzed. Finally, the research on brain-like neuromorphic chips at home and abroad are reviewed. This paper aims to provide learning ideas and research directions for new colleagues in the field of spiking neural network.
Assuntos
Algoritmos , Inteligência Artificial , Encéfalo , Redes Neurais de ComputaçãoRESUMO
Objective To investigate the changes of the neuron-specific enolase(NSE) and soluble intercellar adhesion molecule-1(CAM-1) in serum and cerebrospinal fluid(CSF) in the patients with viral encephhalites (VE). Methods The levels of NSE and sICAM-1 in serum and CSF were determined before and after treatment using ELISA in 58 patients with VE and 20 normal persons. Results The levels of NSE and sICAM-1 in serum before treatment were obviously higher than those of control group, and their differences were significant (P0.05). Conclusions NSE and sICAM-1 may contribute to pathologic course in infection of VE and the levels of NSE and sICAM-1 in serum and CSF may serve as markers of differential diagnosis and clinical significance.