Signed-Power-of-Two (SPT) Neuron Design and Synapse Weight Approximation for Embedded Neural Networks
碩士 === 國立中正大學 === 電機工程研究所 === 106 === Lowering the computation complexity is essential for deep neural networks (DNN) to be integrated into cost- and power-sensitive embedded systems. This thesis first proposes a design-time normalization technique to convert a floating-point DNN model into a fixed...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2017
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/d48y57 |