Title | ||
---|---|---|
Efficient multi-sequence memory with controllable steady-state period and high sequence storage capacity |
Abstract | ||
---|---|---|
Sequential information processing, for instance the sequence memory, plays an important role on many functions of brain. In this paper, multi-sequence memory with controllable steady-state period and high sequence storage capacity is proposed. By introducing a novel exponential kernel sampling function and the sampling interval parameter, the steady-state period can be controlled, and the steady-state time steps are equal to the sampling interval parameter. Furthermore, we explained this phenomenon theoretically. Ascribing to the nonlinear function constitution for local field, the conventional Hebbian learning rule with linear outer product method can be improved. Simulation results show that neural network with nonlinear function constitution can effectively increase sequence storage capacity. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/s00521-010-0453-x | Neural Computing and Applications |
Keywords | DocType | Volume |
sampling interval parameter,efficient multi-sequence memory,steady-state period,sequence memory,nonlinear function constitution,conventional Hebbian,multi-sequence memory,multi-sequence memory � steady-state periodnonlinear function constitution � kernel sampling function,controllable steady-state period,steady-state time step,high sequence storage capacity,sequence storage capacity | Journal | 20 |
Issue | ISSN | Citations |
1 | 1433-3058 | 3 |
PageRank | References | Authors |
0.40 | 6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Min Xia | 1 | 65 | 3.56 |
Yang Tang | 2 | 1310 | 64.50 |
Jian’an Fang | 3 | 40 | 3.99 |
Feng Pan | 4 | 3 | 0.40 |