Adaptive structure generation and neuronal differentiation for memory encoding in SNNs

Zihui Jin, Jian Cai, Yingze Di, Yunlin Lei, Yu Fu, Yuhan Liu, Xu Yang

Abstract: Highlights•This study proposes and constructs a multi-layer spiking neural network model with input, representation, supervision, and observation layers, in which the structure enables our model to exhibit high information capacity and the ability to simulate biological nervous systems, well connecting computer science and biological neuroscience.•This study uses a series of unsupervised connection generating algorithms and bipolar supervised learning algorithm to optimize the structure of the representation layer, achieve functional differentiation of neurons, and enable the network to generate differentiated representations for different data modes.•This study analyzes the abnormal states that are prone to occur in complex spiking neural networks and proposes solutions for situations where the network enters a paralyzed state. The relevant methods provide a new technical path for improving the robustness and stability of spiking neural networks.