Machine learningDeep learning / NLP / CV
多模态多层感知器
多模态多层感知器（MM-MLP）是一种前馈神经网络，它通过分别编码每个数据流并将其融合为共享表示，然后通过全连接层生成分类或回归输出，从而摄取来自两种或多种异构输入模态（例如结构化表格数据、文本嵌入和图像特征向量）的特征。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 689–696. link ↗
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 6: Deep Feedforward Networks). MIT Press. ISBN: 978-0-262-03561-3
如何引用本页
ScholarGate. (2026, June 3). Multimodal Multilayer Perceptron (MM-MLP). ScholarGate. https://scholargate.app/zh/deep-learning/multimodal-multilayer-perceptron
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- 微调多层感知机深度学习↔ compare
- 多层感知机 (MLP)深度学习↔ compare
- 多模态卷积神经网络深度学习↔ compare
- 多模态句子嵌入深度学习↔ compare
- 多模态Transformer深度学习↔ compare