/CSDL-1

Codesmith Deep Learning Cohort 1

Primary LanguageJupyter Notebook

Codesmith Deep Learning Pre-Course

Welcome to Codesmith Deep Learning! In this course, we will develop the experience and expertise required to train, deploy, and analyze deep learning models.

Whether you are a software engineer who wants to know how you can start implementing machine learning models in your current job, a data scientist who wants to add neural networks to their tool belt, or an intermediate/advanced python coder who wants to see what deep learning is all about, this course has something to offer anyone that is interested in neural networks and the future of machine learning.

If you haven't already, please join our slack team - you should have an email from slack inviting you to join the team. We'll use slack throughout the course to share helpful resources and learning materials, ask and answer stack overlow-style questions when people are stuck on coding challenges, and communicate about all things related to this course.

What to expect from the course

We value building an inclusive and supportive community. Above all, you should expect to cultivate empathetic technical and non-technical communication with your peers. After all, engineering doesn't happen in isolation - it happens in teams. If you are kind and thoughtful in your communication, you should expect to build a network of bright and ambitious peers that will help further your career in machine learning.

In addition to community building, the Codesmith team is dedicated to developing ambitious and groundbreaking curriculum and pedagogy. We seek to challenge our program participants to think deeply and engage critically with code they write and with the code their peers write. While we can provide a path for our students to follow, ultimately it's up to each of you to provide the engine that powers you down that path. Put simply, what you put in is what you will get out.

A professor in a research seminar once told me, "the student that learns and creates the most in this seminar will neglect their other studies, they will be singly focused on the research at hand." I was not the student that learned the most in that seminar - I understand that our program participants have jobs and families and many other responsibilities. Part of the reason we've chosen to offer this as an online course is due to the flexibility this affords our participants. But if you are willing and able to put in extra time coding and studying the material covered in instructional hours, you will come away with a fuller understanding of the power and applications of machine learning.

Lastly, you will learn that no code is sacred. Throughout the course, we provide you with some boilerplate code and, occasionally, test cases to guide towards thoughtful, concise solutions to the problems you are expected to solve. Don't take this code for granted. Read it, study it, understand it, and alter it if it doesn't lead you towards the approach that seems most natural to you.

Getting Started

If you have difficulty with the following steps, please let us know in the #help-desk channel on slack!

To begin, you will need a Github account and you will need to install git on your computer. If you haven't done either of these things, please do so now.

  • Create a Github account here
  • Git installation instructions here

After completing the steps above, create your own fork of this repo. To do this, visit this repo on the Codesmith organization on Github. Hit the fork button in the upper right hand corner, and then select your github account. You should be redirected to the new fork you've created.

Now you should clone the fork you've created. hit the green "Clone or download" button and copy the download url that appears. Open up a new terminal window on your computer and navigate to the directory you'd like to store the course materials in. Run the following commands:

  1. git clone <download url you copied>
  2. cd CSDL-<cohort number>
  3. git remote add upstream https://github.com/CodesmithLLC/CSDL-<cohort number>.git

Now you're ready to get started with the precourse! Navigate to the precourse directory and see the README for directions.