Hey there, you want to become a prodigy in Deep learning or looking out for some cool projects to work on? Then you are in the right place. I welcome you the series of Deep Learning posts.

What you get out of this series?

  • In-Depth knowledge in Deep Learning
  • Easy to fiddle code
  • Visualization of things happening in the back-end.

So let's get started with our setup.

What do you need to get things started?

  • Python-3
  • Pip3
  • Numpy for python-3
  • Matplotlib for python-3
  • Jupyter-Notebook

We can use Windows, MAC or Ubuntu. I strongly suggest the use of Ubuntu (It has a lot of community support).

Installation in Ubuntu

Installing python3 and pip

  • You will already have python3 installed in Ubuntu.
  • Press Ctrl+Alt+t to open a terminal
  • Install pip3 by typing this command in terminal.
    $ sudo python3 -m pip install -U pip
    
  • To verify install, type
    $ python3 --version
    
    this would print version of python
  • Now you are good to proceed.

Installing numpy, matplotlib

  • In a terminal, type
    $ sudo -H pip3 install numpy matplotlib
    
  • Now you are done with the installation of numpy and matplotlib

Installing jupyter notebook

  • Open a terminal
  • Type
    $ sudo apt update 
    $ sudo apt-get -y install ipython ipython-notebook 
    $ sudo -H pip3 install jupyter
    
  • To check if it works, type
    $ jupyter notebook
    
    in a terminal
  • The above command will open a session of your home directory in your default browser.
  • Press, Ctrl+c, type y and hit enter in the terminal to stop the jupyter notebook.

Get your hands dirty

  • Lets fire up the jupyter notebook by typing the following in the terminal
    $ jupyter notebook
    
  • This would open a session in your default browser. If not, open a browser and type localhost:8888 in the URL bar.
Start a New notebook in jupyter notebook
  • That opens a new tab in the browser. This is where we code. (yes we will code in a browser)
  • Rename your notebook by changing the untitled to Exercise-1 in the top left corner
Renaming a Notebook

Let us get started by importing the required modules. (Type the following lines in the green box and execute the code by pressing shift+enter)

   In [ 1 ] :   
import numpy as np
import matplotlib.pyplot as plt
print ("Numpy and matplotlib has been successfully installed.")

If everything has been installed without error, then you should see

Numpy and matplotlib has been successfully installed

So what? It works. But What is Numpy and matplotlib?
Numpy is a fundamental package for scientific computing. It fast and efficient implementation of matrix multiplication. Matplotlib is also a package used for visualisation. (Feel free to google on these packages to know more)

Let us create  a list of integers.

   In [ 2 ] :   
list_of_integer = [I for I in range(10)] # creating a list of integers
print (type(list_of_integer)) # prints the type of a variable 
print (list_of_integer) 

This code will create a list of integers from 0 to 9 and store it in list_of_integer.  But these list of integers is not efficient to perform mathematical operations. So we shall convert them to numpy array.

   In [ 3 ] :   
x_axis = np.array(list_of_integer)                                          
print (type(x_axis))
print (x_axis)

This will create the list_of_integer into a numpy array and store it in x_axis. we shall create another numpy array with random values in the following code.

   In [ 4 ] :   
y_axis = np.random.randn(10)                                       
print (y_axis.shape)

Let us plot the x_axis and y_axis in the following code.

   In [ 5 ] :   
plt.plot(x_axis,y_axis)                          
plt.ylabel('Random number')
plt.xlabel('x_axis')
plt.show()

So with this, the setup is complete. You can now save and shut down the kernel. For the original notebook visit my github page.

In my next post, you can expect

  • Easy-Math behind Neural networks
  • Working of a perceptron
  • Implementation of a perceptron
  • Visualization of a perceptron