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 2303.13565cs.LG
收藏

图张量网络:在多个领域设计大规模神经学习系统的直观框架

Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains

Imperial College London(帝国理工学院)

Yao Lei Xu, Kriton Konstantinidis, Danilo P. Mandic

摘要:

尽管张量和张量运算在现代深度学习中无处不在,但在深度学习社区中,使用张量数学来正式设计和描述神经网络的探索仍然不足。为此,我们引入了图张量网络(GTN)框架,这是一个直观而严格的图形框架,用于在规则和不规则域上系统地设计和实现大规模神经学习系统。所提出的框架被证明是足够的一般性,包括许多流行的架构作为特殊情况下,和足够的灵活性,以处理任何和许多数据域上的数据。通过真实数据实验证明了所提出的框架的功能和灵活性,从而提高了性能,大大降低了复杂性成本,凭借张量代数。

英文摘要:

Despite the omnipresence of tensors and tensor operations in modern deep learning, the use of tensor mathematics to formally design and describe neural networks is still under-explored within the deep learning community. To this end, we introduce the Graph Tensor Network (GTN) framework, an intuitive yet rigorous graphical framework for systematically designing and implementing large-scale neural learning systems on both regular and irregular domains. The proposed framework is shown to be general enough to include many popular architectures as special cases, and flexible enough to handle data on any and many data domains. The power and flexibility of the proposed framework is demonstrated through real-data experiments, resulting in improved performance at a drastically lower complexity costs, by virtue of tensor algebra.

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。

↑