Inception v2

2000년 도입 · 논문 15편에서 사용

Inception v2 is the second generation of Inception convolutional neural network architectures which notably uses batch normalization. Other changes include dropping dropout and removing local response normalization, due to the benefits of batch normalization.

출처: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

소개 논문: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift