到目前为止，没有看见别人翻译

第1课

Webpage / Video / Lesson Forum / General Forum

Welcome!

Make sure your GPU environment is set up and you can run Jupyter Notebook

00_notebook_tutorial.ipynb

Four shortcuts:

• <kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">Shift</kbd>+<kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">Enter</kbd>: Runs the code or markdown on a cell

• <kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">Up Arrow</kbd>+<kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">Down Arrow</kbd>: Toggle across cells

• <kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">b</kbd>: Create new cell

• <kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">0</kbd>+<kbd style="box-sizing: border-box; margin: 0px 0.1em; padding: 2px 5px; font-size: 14.4px; color: rgb(255, 255, 255); background: rgb(51, 51, 51); border: 1px solid rgb(173, 179, 185); border-radius: 3px; box-shadow: rgba(0, 0, 0, 0.25) 0px -1px 0px inset; white-space: nowrap; vertical-align: middle; font-family: Monaco, Consolas, "Andale Mono", "DejaVu Sans Mono", monospace;">0</kbd>: Restart Kernel

[2:45]

Jupyter Notebook is a really interesting device for data scientists because it lets you run interactive experiments and give you not just a static piece of information but something you can interactively experiment with.

How to use notebooks and the materials well based on the last three years of experience:

1. Just watch a lesson end to end.

   • Don't try to follow along because it's not really designed to go the speed where you can follow along. It's designed to be something where you just take in the information, you get a general sense of all the pieces, how it all fits together.

   • Then you can go back and go through it more slowly pausing the video, trying things out, making sure that you can do the things that I'm doing and you can try and extend them to do things in your own way.

   • Don't try and stop and understand everything the first time.

You can do world-class practitioner level deep learning [4:31]

[图片上传失败...(image-fe3fa9-1558700881997)]

Main places to be looking for things are:

• http://course-v3.fast.ai/

• https://forums.fast.ai/

A little bit about why we should listen to Jeremy [5:27]

[图片上传失败...(image-bd926d-1558700881997)]

Using machine learning to do useful things [6:48]

[图片上传失败...(image-84aa04-1558700881997)]

[7:26]

[图片上传失败...(image-124f36-1558700881997)]

If you follow along with 10 hours a week or so approach for the 7 weeks, by the end, you will be able to:

1. Build an image classification model on pictures that you choose that will work at a world class level

2. Classify text using whatever datasets you're interested in

3. Make predictions of commercial applications like sales

4. Build recommendation systems such as the one used by Netflix

Not toy examples of any of these but actually things that can come top 10 in Kaggle competitions, that can beat everything that's in the academic community.

The prerequisite is one year of coding and high school math.