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.
Scientific Calculator for Designing Trojan Detectors in Neural Networks
Axle Informatics(Axle Informatics(Axle信息学公司));National Institute of Standards and Technology(美国国家标准与技术研究院);National Institutes of Health (NIH)(美国国立卫生研究院(NIH))
Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Tensorflow Pretrained Models
Georgia Institute of Technology(佐治亚理工学院);Indiana University(印第安纳大学);Kyoto University(京都大学);Rutgers University(罗格斯大学);Purdue University(普渡大学);Emory University(埃默里大学);Sichuan University(四川大学);Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);National Taiwan Normal University(台湾师范大学)
What should a neuron aim for? Designing local objective functions based on information theory
Faculty of Physics, Institute for the Dynamics of Complex Systems, University of Göttingen(物理学院、复杂系统动力学研究所、哥廷根大学);Max Planck Institute for Dynamics and Self-Organization, Göttingen(动态与自我组织马克斯·普朗克研究所,哥廷根);Göttingen Campus Institute for Dynamics of Biological Networks, University of Göttingen(哥廷根校区生物网络动力学研究所、哥廷根大学);Institute of Computer Science and Campus Institute Data Science, University of Göttingen(计算机科学研究所和校园数据科学研究所、哥廷根大学)