arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.06149cs.CV
收藏

深度神经网络的无数据参数修剪

Data-free parameter pruning for Deep Neural Networks

Indian Institute of Science(印度科学院)

Suraj Srinivas, R. Venkatesh Babu

摘要:

具有数百万参数的深度神经网络(NN)是当今许多最先进的计算机视觉系统的核心。然而,最近的工作表明,更小的模型可以实现类似的性能水平。在这项工作中,我们解决的问题,修剪参数的训练NN模型。与以前的工作不同,我们一次移除一个神经元,而不是一次移除一个权重。我们展示了相似的神经元是如何冗余的,并提出了一种系统的方法来去除它们。我们修剪密集连接层的实验表明,我们可以在MNIST训练的网络中删除高达85%的总参数,AlexNet约为35%,而不会显着影响性能。我们的方法可以应用于大多数具有全连接层的网络之上,以提供更小的网络。

英文摘要:

Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work, we address the problem of pruning parameters in a trained NN model. Instead of removing individual weights one at a time as done in previous works, we remove one neuron at a time. We show how similar neurons are redundant, and propose a systematic way to remove them. Our experiments in pruning the densely connected layers show that we can remove upto 85\% of the total parameters in an MNIST-trained network, and about 35\% for AlexNet without significantly affecting performance. Our method can be applied on top of most networks with a fully connected layer to give a smaller network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑