Robust sequence memory in sparsely-connected networks with controllable steady-state period

A novel sparsely-connected neural network for sequence memory with controllable steady-state period is proposed in this study. By introducing a new exponential kernel sampling function and the sampling interval parameter, the steady-state period can be controlled, and the steady-state time steps is equal to the sampling interval parameter. Ascribing to the exponential kernel sampling function, the sequence storage capacity is enlarged compared with the existing sequence memory models. Owning to the sparsely-connected of Gaussian distribution, the model produces the efficient use of synapse resources, but the sequence storage capacity is decreased compared with the fully-connected networks. The study also gives a significant result that the networks of different dimensions have the same synapse connection efficiency if they are with the same connection mean degree.