Geometric algebra based recurrent neural network for multi-dimensional time-series prediction
Recent RNN models deal with various dimensions of MTS as independent channels, which may lead to the loss of dependencies between different dimensions or the loss of associated information between each dimension and the global. To process MTS in a holistic way without losing the inter-relationship a...
Main Authors: | Yanping Li, Yi Wang, Yue Wang, Chunhua Qian, Rui Wang |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-12-01
|
Series: | Frontiers in Computational Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2022.1078150/full |
Similar Items
-
Normed algebras and the geometric series test
by: Robert Kantrowitz, et al.
Published: (2017-11-01) -
Time Series Forecasting and Classification Models Based on Recurrent with Attention Mechanism and Generative Adversarial Networks
by: Kun Zhou, et al.
Published: (2020-12-01) -
Forecasting time series with long short-term memory networks
by: Quoc Dung Nguyen, et al.
Published: (2020-07-01) -
Insights Into LSTM Fully Convolutional Networks for Time Series Classification
by: Fazle Karim, et al.
Published: (2019-01-01) -
n-Dimensional Chaotic Time Series Prediction Method
by: Fang Liu, et al.
Published: (2022-12-01)