3 papers
cs.NE2026
Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction
Huannan Zheng, Jingli Liu, Kezhou Yang
Signed spiking neurons carry richer information than standard spiking neurons. This work proposes a compact magnetic tunnel junction (MTJ)-based neuron for signed leaky integrate-a…
cs.ET2026
Human-like working memory signatures emerge from intrinsically plastic artificial neurons for robust dynamic vision
Jingli Liu, Huannan Zheng, Bohao Zou +1
While the unsustainable energy cost of artificial intelligence necessitates physics-driven computing, its performance superiority over full-precision GPUs remains a challenge. We b…
cs.NE2026
Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian
Huannan Zheng, Jingli Liu, Kezhou Yang
Uncertainty in biological neural systems appears to be computationally beneficial rather than detrimental. However, in neuromorphic computing systems, device variability often limi…