“There is also this one https://arxiv.org/abs/1506.02515 which takes pruning a step further to reduce the sparsity. Also this one https://arxiv.org/abs/1608.04493 which makes sure not to kill any neurons which proves to be useful at a later stage in the pruning process.”
Dynamic Network Surgery for Efficient DNNs
Deep learning has become a ubiquitous technology to improve machine intelligence. However, most of the existing deep models are structurally very complex, making them difficult to be deployed on the mobile platforms with limited computational power. In this paper, we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning. Unlike the previous methods which accomplish this task in a greedy way, we properly incorporate connection splicing into the whole process to avoid incorrect pruning and make it as a continual network maintenance. The effectiveness of our method is proved with experiments. Without any accuracy loss, our method can efficiently compress the number of parameters in LeNet-5 and AlexNet by a factor of $\bm{108}\times$ and $\bm{17.7}\times$ respectively, proving that it outperforms the recent pruning method by considerable margins. Code and some models are available at https://github.com/yiwenguo/Dynamic-Network-Surgery.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“I find the technique very similar to the one presented in [1] from 2018, and I can't seem to find a ref to this paper in theirs. Another interesting and very related paper [2] that they fail to mention also shows improvement in training time (epochs) with dynamic pruning And for the ones who wondered how far this is going back time I suggest you to read…”