首页BatchNormalization

BatchNormalization

时间: 2023-06-19 21:04:37 浏览: 68

Batch Normalization

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

BatchNormalization（批归一化）是一种在深度神经网络中用于加速收敛和提高模型精度的技术。它通过对每个 mini-batch 的输入进行归一化，即将其缩放到均值为0，方差为1的分布上，从而使得网络更容易训练。BatchNormalization还引入了两个可学习的参数，用于恢复模型的表达能力。BatchNormalization可以被添加到神经网络中的任何层中，通常在激活函数之前。

阅读全文