We are going to run a series of experiments where you learn AI on your own by experimenting.

Here are the tools required for us to start experimenting with AI.

  • VSCode (Pytorch snippets, Python)
  • Conda
  • Pytorch + Tensorboard
  • Git and an account with Github

You need to do the following

Step 1:

Create a conda environment and install pytorch library inside the environment

conda create -n teamatom python=3
conda activate teamatom

Step 2:

Install pytorch based on your cuda version. Follow the instructions on this page.

PyTorch
An open source machine learning framework that accelerates the path from research prototyping to production deployment.

Step 3:

Install VSCode on your system.

Download Visual Studio Code - Mac, Linux, Windows
Visual Studio Code is free and available on your favorite platform - Linux, macOS, and Windows. Download Visual Studio Code to experience a redefined code editor, optimized for building and debugging modern web and cloud applications.

If you don't have a powerful system for mnist experiments use online tools like

  • Google Colab (gpu, tpu, no-git)
  • Deepnote (no gpu, git available)

Step 4:

View all videos here and understand what neural netowrks are so we can go ahead and implement them.

Neural networks
Share your videos with friends, family, and the world

If you want to be part of this program drop us a mail at discover@atom360.io