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.
CITATION STYLE
Lyu, J., & Sheen, S. (2020). A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spotting. In Advances in Intelligent Systems and Computing (Vol. 1121 AISC, pp. 243–254). Springer. https://doi.org/10.1007/978-3-030-38364-0_22
Mendeley helps you to discover research relevant for your work.