文件名称:Dynamic_Deep_Neural_Networks
介绍说明－－下载内容均来自于网络，请自行研究使用
We introduce Dynamic Deep Neural Networks (D2NN),
a new type of feed-forward deep neural network that allows
selective execution. Given an input, only a subset of D2NN
neurons are executed, and the particular subset is determined
by the D2NN itself. By pruning unnecessary computation
depending on input, D2NNs provide a way to improve
computational efficiency. To achieve dynamic selective
execution, a D2NN augments a feed-forward deep neural
network (directed acyclic graph of differentiable modules)
with controller modules. Each controller module is
a sub-network whose output is a decision that controls
whether other modules can execute.
a new type of feed-forward deep neural network that allows
selective execution. Given an input, only a subset of D2NN
neurons are executed, and the particular subset is determined
by the D2NN itself. By pruning unnecessary computation
depending on input, D2NNs provide a way to improve
computational efficiency. To achieve dynamic selective
execution, a D2NN augments a feed-forward deep neural
network (directed acyclic graph of differentiable modules)
with controller modules. Each controller module is
a sub-network whose output is a decision that controls
whether other modules can execute.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
| 文件名 | 大小 | 更新时间 |
|---|---|---|
| AC2.Dynamic Deep Neural Networks- Optimizing Accuracy-Efficiency Trade-offs by Selective Execution.pdf | 1489007 | 2018-02-07 |