.png){kind=icon}
返回
Variational tensor neural networks for deep learning
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-024-69366-8.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN) into NN frameworks, combined with a variational DMRG-inspired training technique. This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. Our variational algorithm utilizes a local gradient-descent technique, enabling manual or automatic computation of tensor gradients, facilitating design of hybrid TNN models with combined dense and tensor layers. Our training algorithm further provides insight on the entanglement structure of the tensorized trainable weights and correlation among the model parameters. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.
Keyword:
MATRIX PRODUCT STATES
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.9
论文数:
28.3W
被引数:
83.5W
机构
引用论文
分享收藏Matrix product states, projected entangled pair states, and variational renormalization group methods for quantum spin systems量子自旋系统的矩阵乘积态，投影纠缠态和变分重归一化组方法.png)
ADVANCES IN PHYSICS
OAAI
ADVANCES IN PHYSICSIF13.8
OAAI分享收藏Theoretical error performance analysis for variational quantum circuit based functional regressionOAAI
OAAI分享收藏Neural tensor contractions and the expressive power of deep neural quantum statesPHYSICAL REVIEW BOAAI
PHYSICAL REVIEW BIF3.7
OAAI分享收藏
查看更多内容