方法证据记录
Batch Normalization
Batch Normalization is a training technique introduced by Sergey Ioffe and Christian Szegedy in 2015 that normalizes the pre-activation outputs of each layer using the mean and variance computed over the current mini-batch. By stabilizing the input distribution to each layer throughout training, it substantially reduces internal covariate shift, enabling the use of higher learning rates and making deep networks train faster and more reliably.
源记录
引文逐字复制自方法源记录。这些引文不代表任何层级的验证。
Batch Normalization (Normalizing Layer Activations per Mini-Batch)
分类方法记录 · ml-model / deep-learning
- Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), PMLR 37, 448–456. · URL
- Goodfellow, I., Bengio, Y. & Courville, A. (2016). Deep Learning (Ch. 8). MIT Press. · ISBN 978-0-262-03561-3
- Ioffe, S. & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:1502.03167. · URL
精选声明
声明已持久化到证据分类账中，每个声明都有自己的评估。
尚无精选声明
当分类账中没有声明时，此视图不会自行创建声明评估。
相关方法
从方法图中生成，显示为机器建议的关系 — 不推断任何证据声明。