Name
Abstract | ||
|---|---|---|
In the brain, the discrete elements in a temporal order is encoded as a sequence memory. At the neural level, the reproducible sequence order of neural activity is very crucial for many cases. In this paper, a mechanism for oscillation in the network has been proposed to realize the sequence memory. The mechanism for oscillation in the network that cooperates with hetero-association can help the network oscillate between the stored patterns, leading to the sequence memory. Due to the oscillatory mechanism, the firing history will not be sampled, the stability of the sequence is increased, and the evolvement of neurons’ states only depends on the current states. The simulation results show that neural network can effectively achieve sequence memory with our proposed model. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1007/s11432-013-4998-z | SCIENCE CHINA Information Sciences |
Keywords | Field | DocType |
neural network, hetero-association, sequence memory, oscillation, Hebbian rule | Oscillation,Recurrent neural network,Neural activity,Time delay neural network,Hebbian theory,Artificial intelligence,Artificial neural network,Mathematics | Journal |
Volume | Issue | ISSN |
57 | 7 | 1869-1919 |
Citations | PageRank | References |
12 | 0.38 | 13 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Min Xia | 1 | 65 | 3.56 |
| Liguo Weng | 2 | 46 | 6.53 |
| Zhijie Wang | 3 | 89 | 11.14 |
| Jian-an Fang | 4 | 529 | 23.40 |