方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 长短期记忆网络× | 自编码器× | 卷积神经网络（分类）× | |
|---|---|---|---|
| 领域 | 深度学习 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning | Machine learning |
| 起源年份≠ | 1997 | 2006 | 1998 |
| 提出者≠ | Hochreiter, S. & Schmidhuber, J. | Hinton, G.E. & Salakhutdinov, R.R. | LeCun, Y. et al. |
| 类型≠ | Recurrent neural network (gated memory cell) | Neural network (encoder-decoder) | Deep neural network (convolutional) |
| 开创性文献≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗ | LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324. DOI ↗ |
| 别名 | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network | CNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifier |
| 相关≠ | 5 | 4 | 5 |
| 摘要≠ | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. | An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data. | A Convolutional Neural Network (CNN) is a deep learning model, established by LeCun and colleagues in 1998, that learns local patterns directly from images and structured data to classify them. Stacks of convolutional filters discover increasingly abstract features, so manual feature engineering can be largely reduced. |
| ScholarGate数据集 ↗ |
|
|
|