STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Dennis, Hu, Jerry Yao-Chieh, Li, Weijian, Chen, Bo-Yu, Liu, Han
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916076242075648
author Wu, Dennis
Hu, Jerry Yao-Chieh
Li, Weijian
Chen, Bo-Yu
Liu, Han
author_facet Wu, Dennis
Hu, Jerry Yao-Chieh
Li, Weijian
Chen, Bo-Yu
Liu, Han
contents We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series prediction with memory-enhanced capabilities. At the heart of our approach is STanHop, a novel Hopfield-based neural network block, which sparsely learns and stores both temporal and cross-series representations in a data-dependent fashion. In essence, STanHop sequentially learn temporal representation and cross-series representation using two tandem sparse Hopfield layers. In addition, StanHop incorporates two additional external memory modules: a Plug-and-Play module and a Tune-and-Play module for train-less and task-aware memory-enhancements, respectively. They allow StanHop-Net to swiftly respond to certain sudden events. Methodologically, we construct the StanHop-Net by stacking STanHop blocks in a hierarchical fashion, enabling multi-resolution feature extraction with resolution-specific sparsity. Theoretically, we introduce a sparse extension of the modern Hopfield model (Generalized Sparse Modern Hopfield Model) and show that it endows a tighter memory retrieval error compared to the dense counterpart without sacrificing memory capacity. Empirically, we validate the efficacy of our framework on both synthetic and real-world settings.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17346
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
Wu, Dennis
Hu, Jerry Yao-Chieh
Li, Weijian
Chen, Bo-Yu
Liu, Han
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series prediction with memory-enhanced capabilities. At the heart of our approach is STanHop, a novel Hopfield-based neural network block, which sparsely learns and stores both temporal and cross-series representations in a data-dependent fashion. In essence, STanHop sequentially learn temporal representation and cross-series representation using two tandem sparse Hopfield layers. In addition, StanHop incorporates two additional external memory modules: a Plug-and-Play module and a Tune-and-Play module for train-less and task-aware memory-enhancements, respectively. They allow StanHop-Net to swiftly respond to certain sudden events. Methodologically, we construct the StanHop-Net by stacking STanHop blocks in a hierarchical fashion, enabling multi-resolution feature extraction with resolution-specific sparsity. Theoretically, we introduce a sparse extension of the modern Hopfield model (Generalized Sparse Modern Hopfield Model) and show that it endows a tighter memory retrieval error compared to the dense counterpart without sacrificing memory capacity. Empirically, we validate the efficacy of our framework on both synthetic and real-world settings.
title STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2312.17346