目录

• Supervised Learning
• Massive Unlabeled data
• Unsupervised Learning
• Why needed

Supervised Learning

Massive Unlabeled data

Unsupervised Learning

Why needed

• Dimension reduction

• Preprocessing:Huge dimension, say 224*224, is hard to process

• Visualization:https://projector.tensorflow.org/

• Taking advantages of unsupervised data

• Compression, denoising, super-resolution...