Direct training via backpropagation for ultra-low-latency spiking neural networks with multi-threshold

HIGHLIGHTS

• who: Changqing Xu et al. from the Guangzhou Institute of Technology, Xidian University, Xi`an, China have published the paper: Direct Training via Backpropagation for Ultra-Low-Latency Spiking Neural Networks with Multi-Threshold, in the Journal: Symmetry 2022, 14, 1933. of /2022/
• what: To overcome this problem the authors propose a novel method based on backpropagation (BP) for (1-2 time steps) SNNs with multi-threshold. The authors propose an architecture of SNN with multi-threshold LIF models, which can transmit and process more information at each time step, and the corresponding direct training . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.