图 书 馆
有限数值精度的深度学习Deep Learning with Limited Numerical Precision |
|
| 课程网址: | http://videolectures.net/icml2015_gupta_numerical_precision/ |
| 主讲教师: | Suyog Gupta |
| 开课单位: | IBM |
| 开课时间: | 2015-12-05 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Training of large-scale deep neural networks is often constrained by the available computational resources. We study the effect of limited precision data representation and computation on neural network training. Within the context of low-precision fixed-point computations, we observe the rounding scheme to play a crucial role in determining the network’s behavior during training. Our results show that deep networks can be trained using only 16-bit wide fixed-point number representation when using stochastic rounding, and incur little to no degradation in the classification accuracy. We also demonstrate an energy-efficient hardware accelerator that implements low-precision fixed-point arithmetic with stochastic rounding |
| 关 键 词: | 深度神经网络; 有限精度; 节能硬件加速器 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-11-29：chenjy |
| 最后编审: | 2022-11-29：chenjy |
| 阅读次数: | 41 |