手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| 多層パーセプトロン (MLP)× | TimeMixer: 時系列予測のための分解可能マルチスケール混合× | |
|---|---|---|
| 分野 | 深層学習 | 深層学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 1986 | 2024 |
| 提唱者≠ | Rumelhart, D. E.; Hinton, G. E.; Williams, R. J. | Shiyu Wang et al. |
| 種類≠ | Supervised feedforward neural network | MLP-based multiscale time-series forecasting model |
| 原典≠ | Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323, 533–536. DOI ↗ | Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J. Y., & Zhou, J. (2024). TimeMixer: Decomposable multiscale mixing for time series forecasting. ICLR. link ↗ |
| 別名≠ | MLP, feedforward neural network, fully connected neural network, vanilla neural network | Decomposable Multiscale Mixing, Multiscale Time-Series Mixer, TimeMixer Model, Çok Ölçekli Zaman Serisi Karıştırıcı |
| 関連≠ | 4 | 3 |
| 概要≠ | A Multilayer Perceptron is a classic fully connected feedforward neural network trained with the backpropagation algorithm, as formalised by Rumelhart, Hinton & Williams in their landmark 1986 Nature paper. Composed of an input layer, one or more hidden layers of neurons, and an output layer, the MLP learns nonlinear mappings from input features to target outputs and serves as the foundational building block of modern deep learning. | TimeMixer is a decomposition-based, attention-free time-series forecasting architecture introduced by Wang et al. at ICLR 2024. The central idea is to disentangle seasonal and trend components across multiple temporal scales constructed by average pooling, then mix information across those scales using lightweight MLP blocks. By handling coarse (trend-dominant) and fine (seasonal-dominant) resolutions separately and combining their predictions, TimeMixer avoids the quadratic cost of attention while capturing both local and global temporal patterns. |
| ScholarGateデータセット ↗ |
|
|