A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting
A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting
复制标题
DOI：
10.1007/978-3-030-38364-0_22
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
J. Lyu;S. Sheen
中科院分区：
文献类型：
--
作者：
J. Lyu;S. Sheen
我们研究了信道数量减少与权重二值化（1位权重精度）相结合，以修剪卷积神经网络用于关键字定位（分类）任务。我们采用了基于组Lasso惩罚的组分裂方法，以实现超过50%的信道稀疏性，同时保持网络性能在0.25%的准确性损失。我们展示了一个有效的三阶段过程来平衡网络训练的准确性和稀疏性。
We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) task. We adopt a group-wise splitting method based on the group Lasso penalty to achieve over 50% channel sparsity while maintaining the network performance within 0.25% accuracy loss. We show an effective three-stage procedure to balance accuracy and sparsity in network training.