## How to Build a Simple Neural Network From the Scratch(Step by Step)

This video explains How to Build a Simple Neural Network in Python(Step by Step) with Jupyter Notebook

To Learn Python: www.kindsonthegenius.com/python
Machine Learning 101: https://www.kindsonthegenius.com/2019

Learn R for Data Science – https://www.youtube.com/playlist?list=PLMz1vLpcJgGCZbw-yOX7_GO8tI0owAw64

Subscribe Kindson The Tech Pro Youtube: https://bit.ly/2PpJd8Q
Join my group ICS on Facebook: https://bit.ly/2UULiQj
Follow me on Instagram – https://www.instagram.com/kindsonm/
Learn about me: http://www.kindsonthegenius.com

Learn How to create a neural network in Python, a very important concept in Machine Learning and Data Science

Source

### Comment List

• Kindson The Tech Pro
January 10, 2021

the derivative of sigmoid equals to the sigmoid times one minus sigmoid

ddxσ(x)=σ(x)(1−σ(x))

in your nonlin fuction

def nonlin(x, deriv=False):

if(deriv):

return (1/(1+np.exp(-x)))*(1-1/(1+np.exp(-x)))

return 1/(1+np.exp(-x))

kept your code structure but it's not pythonic, try to keep the functions separate like:

def sigmoid(x):

return 1/(1+np.exp(-x))

def deriv_sigmoid(x):

return sigmoid(x) * (1 – sigmoid(x))

also, please review your series, and double check your facts, you have very obvious mistakes that might misguide beginners

keep it up, you're a good teacher

• Kindson The Tech Pro
January 10, 2021

Hi，what if you dont have the output y, and you want to set it yourself to predict?
Need help for project.

• Kindson The Tech Pro
January 10, 2021

new subscriber here .. cheers!!!

• Kindson The Tech Pro
January 10, 2021

I did not understand that last part from delta_l1🥺