图 书 馆
使用哈希技巧压缩神经网络Compressing Neural Networks with the Hashing Trick |
|
| 课程网址: | http://videolectures.net/icml2015_weinberger_neural_networks/ |
| 主讲教师: | Kilian Q. Weinberger |
| 开课单位: | 康奈尔大学 |
| 开课时间: | 2015-12-05 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | As deep nets are increasingly used in applications suited for mobile devices, a fundamental dilemma becomes apparent: the trend in deep learning is to grow models to absorb ever-increasing data set sizes; however mobile devices are designed with very little memory and cannot store such large models. We present a novel network architecture, HashedNets, that exploits inherent redundancy in neural networks to achieve drastic reductions in model sizes. HashedNets uses a low-cost hash function to randomly group connection weights into hash buckets, and all connections within the same hash bucket share a single parameter value. These parameters are tuned to adjust to the HashedNets weight sharing architecture with standard backprop during training. Our hashing procedure introduces no additional memory overhead, and we demonstrate on several benchmark data sets that HashedNets shrink the storage requirements of neural networks substantially while mostly preserving generalization performance. |
| 关 键 词: | 深度网络; 神经网络; 机器学习 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-12-14：wujk |
| 最后编审: | 2023-12-14：wujk |
| 阅读次数: | 23 |