Tensorial Recurrent Neural Networks for Longitudinal Data Analysis

2017/08/01 by Mingyuan Bai, Bai, Mingyuan, Boyan Zhang +3 · 1 citation
Computer Science · Mathematics · #Computational Physics and Python Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Tensor decomposition and applications

paper · pdf · doi:10.48550/arxiv.1708.00185

openalex publication_date 2017/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads to the loss of the precise information of the spatial or longitudinal dimensions. In addition, such a vectorized data is not an optimum solution for learning the representation of the longitudinal data. In this paper, we propose a new variant of tensorial neural networks which directly take tensorial time series data as inputs. We call this new variant as Tensorial Recurrent Neural Network (TRNN). The proposed TRNN is based on tensor Tucker decomposition.

Cited by

• Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition

Related

• Tensor Decomposition for Compressing Recurrent Neural Network
• Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
• Tensor-on-tensor Regression Neural Networks for Process Modeling with High-dimensional Data
• Generalized Tensor Models for Recurrent Neural Networks
• An Efficient Approach to Regression Problems with Tensor Neural Networks