Sigma-delta modulation neural networks

It is shown that sigma-delta (Σ-Δ) modulation can be used to model the information coding process of biological neurons. Signal analysis results demonstrate that Σ-Δ modulation processes a noise shaping property by which signal and noise are separated into low (baseband) and high frequency bands, respectively. Restoring the signal with high S/N ratio can be accomplished with a lowpass filter. This property is used to demonstrate that Σ-Δ modulation can outperform stochastic logic in terms of coding accuracy. The results of simulation on a Σ-Δ modulation Hopfield neural network are presented. They demonstrate that Σ-Δ modulation can significantly improve the performance of the network on the immunity of falling into false states. The addition of noise can help Σ-Δ modulation neural networks escape from one locally stable state to another