Lots of people wan to start with neural networks and machine learning and I’m one of the. I’ve decided to share my progress in some kind of series, because teching someone is even better method of learning for me.


Where to start?
Disclaimer: Math i very useful, so start with it. I won’t explain basics, so you proably want to start with KhanAcademy or something similar. The most seful are:
1. Calculus
2. Discrete mathematics (especially graphs & combinatorics).

I’m learning from FreeCodeCamp Tutorial by Tim Ruscica (Tech with Tim).


Installation

I’m using minicond3 on Linux - it’s the easiest way to use TensorFlow in my opinion. We an create virtual environments here.


Miniconda3 insallation
Download proper intallation file from here. Next run

  bash <<minicondainstallation_file>>

Congratulations! Your conda is installed. Restart your terminal and you could see somethin like (base) at the beginning of your prompt. You may notice that pakages installed with pip are not available anymore. You can disable enering base environment with:

  conda config --st auto_activate_base false

Restart your termial once again and everything should be just like before installing onda (but it’s still installed of course).

You can now createnew environment with

  conda create --name env_name

and activate it wih

  conda activate env_name


TensorFlow installation

Conda is now instaled and set up, so it’s time to start with TF. It’s as easy as

  conda install tesorflow-gpu -c conda-forge

If you have nVidia GPU. Just drop the -gpu suffix if you don’t want to use it. Some usefu packages are:
1. numpy - blazing fast arrays
2. pandas - dataframes
3. matplotlib - my tool of choice for (guess what :v) plots
4. jupyterlab - better version of jupyter, but I’m using PyCharm, so t doesn’t matter to me.

That’s all for now I’ll post some new content soon(tm).