| 发明名称 |
LONG SHORT-TERM MEMORY USING A SPIKING NEURAL NETWORK |
| 摘要 |
A method for configuring long short-term memory (LSTM) in a spiking neural network includes decoding input spikes into analog values within the LSTM. The method further includes implementing the LSTM based on an encoded representation of the analog values. The implementing can include encoding the analog values using base expansive coding, rate coding, latency coding or synaptic weight coding. |
| 申请公布号 |
US2016034812(A1) |
申请公布日期 |
2016.02.04 |
| 申请号 |
US201414527679 |
申请日期 |
2014.10.29 |
| 申请人 |
QUALCOMM Incorporated |
发明人 |
GIBSON Sarah Paige;LIU Yinyin |
| 分类号 |
G06N3/08 |
主分类号 |
G06N3/08 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A method for configuring long short-term memory (LSTM) in a spiking neural network, comprising:
decoding input spikes into analog values within the LSTM; and implementing the LSTM based at least in part on an encoded representation of the analog values. |
| 地址 |
San Diego CA US |
