Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验

本文章内容:

Coursera吴恩达深度学习课程,

第四课: 卷积神经网络(Convolutional Neural Networks)

第四周:特殊应用:人脸识别和神经风格转换(Special applications: Face recognition &Neural style transfer)

测验

 

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第1张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第2张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第3张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第4张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第5张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第6张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第7张图片

cost function 没有用到Y啊?

Is Neural Style Transfer considered supervised or unsupervised learning?

Neural style transfer is not really machine learning, but an interesting side effect/output of machine learning on image tasks. When performing neural style transfer using a pre-trained model, then a significant amount of supervised machine learning has already occurred to enable it.

The style transfer algorithm is still an example of gradient-based cost function optimisation, which it shares with many supervised and unsupervised learning algorithms.

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第8张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第9张图片

Coursera-吴恩达-深度学习-第四门课-卷积神经网络 -week4-测验_第10张图片

 

 

 

 

 

你可能感兴趣的:(Deep,learning)