权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Tensor Network Representation for Machine Learning: Theoretical Study and Algorithms Development

机器学习的张量网络表示：理论研究和算法开发

基本信息

批准号：
20H04249
负责人：
ZHAO QIBIN
金额：
$ 11.23万
依托单位：
Institute of Physical and Chemical Research
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (B)
财政年份：
2020
资助国家：
日本
起止时间：
2020-04-01 至 2024-03-31
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20H04249/
关键词：
Tensor networks machine learning Tensor Networks Machine Learning Robustness tensor network

项目摘要

We have developed several new tensor network decomposition and completion algorithms, and also developed the tensor network based neural network models and learning algorithms. These methods have been applied to several computer vision tasks.Specifically, we have developed tensorized RNN model that can achieve long term memory and reduced model size; we also studied Bayesian latent factor models to understand how tensor network is able to achieve model compression; our proposed tensor fusion layer can be applied to image denoting tasks with improvement performance, which can be also applied to the development of multimodal sentimental analysis. We also developed an efficient algorithm for classification on incomplete data samples, which has practical applications when the high-quality dataset is difficult to be obtained.From theoretical perspective, we have studied tensor nuclear norm and proposed several new definition of tensor norm, which has guarantee for exact recovery to tensor. In addition, we proposed a new type tensor network, called fully connected tensor network, which shows great flexibility on modeling complex interaction between tensor modes. The effectiveness of our theory and model is validated extensively on tensor completion tasks.

我们开发了几种新的张量网络分解和完备化算法，并开发了基于张量网络的神经网络模型和学习算法。这些方法已应用于多个计算机视觉任务。具体来说，我们开发了张量化RNN模型，可以实现长期记忆并减少模型大小;我们还研究了贝叶斯潜在因子模型，以了解张量网络如何实现模型压缩;我们提出的张量融合层可以应用于具有改进性能的图像表示任务，这也可以应用于多模态情感分析的开发。从理论上研究了张量核范数，提出了几种新的张量范数定义，为张量的精确恢复提供了保证。此外，我们还提出了一种新的张量网络，称为全连接张量网络，它在模拟张量模式之间的复杂相互作用方面表现出很大的灵活性。我们的理论和模型的有效性得到了广泛的验证张量完成任务。

项目成果

期刊论文数量（17）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

TPFN: Applying Outer Product Along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data

DOI：
10.1007/978-3-030-58586-0_26
发表时间：
2020
期刊：
影响因子：
0
作者：
Binghua Li;Chao Li;Feng Duan;Ning Zheng;Qibin Zhao
通讯作者：
Binghua Li;Chao Li;Feng Duan;Ning Zheng;Qibin Zhao

Tensor Recovery via L-Spectral k-Support Norm

通过 L 谱 k 支持范数恢复张量

DOI：
10.1109/jstsp.2021.3058763
发表时间：
2021
期刊：
IEEE Journal of Selected Topics in Signal Processing
影响因子：
7.5
作者：
Andong Wang;Guoxu Zhou;Zhong Jin;Qibin Zhao
通讯作者：
Qibin Zhao

Learning from Incomplete Features by Simultaneous Training of Neural Networks and Sparse Coding

DOI：
10.1109/cvprw53098.2021.00296
发表时间：
2021-06
期刊：
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
影响因子：
0
作者：
C. Caiafa;Ziyao Wang;Jordi Solé-Casals;Qibin Zhao
通讯作者：
C. Caiafa;Ziyao Wang;Jordi Solé-Casals;Qibin Zhao

Tensor Decomposition Via Core Tensor Networks

DOI：
10.1109/icassp39728.2021.9413637
发表时间：
2021-06
期刊：
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
0
作者：
Jianfu Zhang;Zerui Tao;Liqing Zhang;Qibin Zhao
通讯作者：
Jianfu Zhang;Zerui Tao;Liqing Zhang;Qibin Zhao

Hide Chopin in the Music: Efficient Information Steganography Via Random Shuffling

将肖邦隐藏在音乐中：通过随机洗牌实现高效信息隐写术