arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.09635cs.LG
收藏

Tucker分解网络的表达能力及其比较

Tucker Decomposition Network: Expressive Power and Comparison

Hong Kong Baptist University(香港浸会大学);Université de Mons(蒙斯大学)

Ye Liu, Junjun Pan, Michael Ng

摘要:

深度神经网络在解决许多机器学习和计算机视觉问题方面取得了巨大成功。本文的主要贡献是开发了一个基于Tucker张量分解的深度网络,并分析了其表达能力。结果表明,Tucker网络的表达能力比浅层网络更强。一般来说,需要在浅网络中使用指数数量的节点来表示塔克网络。实验结果表明,Tucker网络在图像分类问题中具有良好的应用前景.

英文摘要:

Deep neural networks have achieved a great success in solving many machine learning and computer vision problems. The main contribution of this paper is to develop a deep network based on Tucker tensor decomposition, and analyze its expressive power. It is shown that the expressiveness of Tucker network is more powerful than that of shallow network. In general, it is required to use an exponential number of nodes in a shallow network in order to represent a Tucker network. Experimental results are also given to compare the performance of the proposed Tucker network with hierarchical tensor network and shallow network, and demonstrate the usefulness of Tucker network in image classification problems.

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。

↑