So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| MICN: Mạng tích chập đẳng cự đa tỷ lệ cho dự báo chuỗi thời gian dài hạn× | SCINet: Mạng Tích chập và Tương tác Mẫu cho Dự báo Chuỗi Thời gian× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2023 | 2022 |
| Người khởi xướng≠ | Huiqiang Wang et al. | Minhao Liu et al. |
| Loại≠ | CNN-based time-series forecasting architecture | Hierarchical convolutional time-series forecasting network |
| Công trình gốc≠ | Wang, H., Peng, J., Huang, F., Wang, J., Chen, J., & Xiao, Y. (2023). MICN: Multi-scale local and global context modeling for long-term series forecasting. ICLR. link ↗ | Liu, M., Zeng, A., Chen, M., Xu, Z., Lai, Q., Ma, L., & Xu, Q. (2022). SCINet: Time series modeling and forecasting with sample convolution and interaction. NeurIPS. link ↗ |
| Tên gọi khác | Multi-scale Isometric Convolution Network, Multi-scale Local and Global Context Model, MICN Forecaster, Çok Ölçekli İzometrik Evrişim Ağı | Sample Convolution and Interaction Network, SCI-Net, Temporal Downsampling Convolution Network, Örneklem Evrişim ve Etkileşim Ağı |
| Liên quan | 2 | 2 |
| Tóm tắt≠ | MICN (Multi-scale Isometric Convolution Network) is a convolutional neural network architecture for long-term time-series forecasting introduced by Huiqiang Wang and colleagues at ICLR 2023. Its central idea is to capture both local temporal patterns and global seasonal dependencies simultaneously through multi-scale isometric convolutions combined with a merge attention mechanism, enabling efficient and expressive modeling of complex temporal dynamics without the quadratic cost of full self-attention. | SCINet is a deep learning architecture for multi-step time-series forecasting introduced by Liu et al. at NeurIPS 2022. Its core idea is a recursive binary-tree structure of SCI-Blocks, each of which splits an input sequence into odd- and even-indexed sub-sequences, applies convolutional filters to model cross-subsequence interactions, and then merges the learned representations. This hierarchical downsampling strategy enables the network to capture temporal dependencies at multiple resolutions simultaneously. |
| ScholarGateBộ dữ liệu ↗ |
|
|