A Multi-objective transfer learning framework for time series forecasting with Concept Echo State Networks.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

This paper introduces a novel transfer learning framework for time series forecasting that uses Concept Echo State Network (CESN) and a multi-objective optimization strategy. Our approach addresses the challenges of feature extraction and knowledge transfer in heterogeneous data environments. By optimizing CESN for each data source, we extract targeted features that capture the unique characteristics of individual datasets. Additionally, our multi-network architecture enables effective knowledge sharing among different ESNs, leading to improved forecasting performance. To further enhance efficiency, CESN reduces the need for extensive hyperparameter tuning by focusing on optimizing only the concept matrix and output weights. Our proposed framework offers a promising solution for forecasting problems where data is diverse, limited, or missing.

Authors

  • Yingqin Zhu
    CINVESTAV-IPN Departamento de Control Automático, Av. IPN 2508, Mexico city, 07360, Mexico.
  • Wen Yu
    2 Department of Radiotherapy, Shanghai Chest Hospital, Shanghai Jiao Tong University , Shanghai , China.
  • Xiaoou Li
    Shanghai University of Medicine & Health Science, School of Medical Instrument, 257 Tianxiong Road, Pudong New District, Shanghai 201318, China.