1. Introduction to Deep Learning
Li Mu
Station B: https://space.bilibili.com/1567748478/channel/seriesdetail?sid=358497
Course homepage: https://courses.d2l.ai/zh-v2/
Textbook: https://zh-v2.d2l.ai/
Courseware: https://courses.d2l.ai/zh-v2/assets/pdfs/part-0_2.pdf
1. AI
Development
① Natural language processing is currently still limited to perception. Things that people can react to in a few seconds belong to the scope of perception, even if it is like translating Chinese into English and English into Chinese.
② Computer vision can do some reasoning in the picture.
③ There are symbols in natural language processing, so there is semiotics, and probabilistic models and machine learning can also be used. Computer vision is about pictures, which are filled with pixels. Pixels are difficult to explain with semiotics, so computer vision is mostly explained with probability models and machine learning.
④ Deep learning is a method in computer vision, and it has other application methods.
2. Application
2.1 Image classification
Deep learning first made a relatively big breakthrough in image classification. IMAGENET
It is a relatively large image classification data set, as shown in the figure below, it includes pictures of one thousand categories of natural objects, and it has about one million pictures.
In 2017