Implement Neural Network In Python | Deep Learning Tutorial 13 (Tensorflow2.0, Keras & Python)

In this video we will implement a simple neural network with single neuron from scratch in python. This is also an implementation of a logistic regression in python from scratch. You know that logistic regression can be thought of as a simple neural network. The pre requisite for this tutorial is the previous tutorial on gradient descent (link below). We will be using gradient descent python funciton written in previous video to implement our own custom neural network class.

🔖 Hashtags 🔖
#NeuralNetworkPython #NeuralNetworkdeeplearning #NeuralNetwork #implementneuralnetwork #gradientdescentpython

Prerequisites for this series:   

[adiflorense]

7:18 thank you very much sir, your knowledge is extraordinary You can create your own neural network class without the help of modules. and it turns out it's not as difficult as I imagined

[prasanjain]

The concept and courses given by you is just awesome and u are so much best that no body can ...hats off too you man

[raghavendrac]

Your videos are better than any paid course. Thank you sir!

[Ankurkumar]

Eagerly waiting for a new release in this amazing series....thanks a lot Dhaval Sir....request to make this series very comprehensive....includes transfer learning kind of concepts also if possible. Thanks once again :)

[SachinChauhan-chel]

Great!
I followed this and it was an amazing experience to write this code :)

[karthikc]

Hope you are celebrating this day with joy
Thank you sir

[AshfaqueKhowaja]

You are highly appreciated for this lecture series

[amirman]

great video, both in understanding the neural network basic concepts and at the code level.

[hariharanm]

No words in describing you, my teacher

[sandiproy]

Very nice explanation using codes. Very good teaching skills. Feeling happy.

[AmirMahdi]

Thank you very much, keep up the great content bro

[oprotectordm]

it is a logistics class or ANN ...Where is hidden and output layer @codebasics

[vishaljaiswar]

Sir, thnk you very much
Thnks for quality content
You r great. I have no words for u sir!

[mutaharkamran]

Can you also explain how to implement Hidden layers in this model? and also maybe using 3 or 4 features instead of 2

[chetansingla]

Sir many requests
Can we see predicted values and compare with original values...
Second can we build a model which have multiple inputs and output
How to generate equation of inputs with output if output is in 0, 1, 2, 3

[hardikvegad]

Sir if we have hundreds of columns without the name. Then how can we name them using pandas and a for loop or lambda function because if we try to name them using names=[] it will be a very time-consuming process. The name of the columns can be col1, col2, col3...etc.

[UdayKiran-mwcr]

I am expecting from scratch means without importing any library like tensorflow. I saw many videos with same title but inside they import tensorflow.

[krishnakishorepeddisetti]

Video shows as neutral neutral network sir ...I mean the home page look.. kindly correct it

[harshvardhanpardeshi]

@codebasics The training of the model stops at random epoch. There is no error shown by python, tensorflow or notebook. How did you run 5000 epochs at once? How to fix this issue?

[KANAVSINGHRANA]

Why is your customModel.predict() function not taking values of self.w1, self.w2, self.bias values as 1, 1, 0 respectively. Why is it taking value from gradient_descent() even though it never runs for customModel.predict()? Please clarify