Neural Networks [Machine Learning] #4: Python Implementation

preview_player
Показать описание

In this video, I explain the code behind a basic Neural Network (a machine learning model). Note that I am not using a library as the code for the Neural Network.

I begin by explaining the functions of all the lines of code. I don't aim to teach the actual python programming language in much detail, so you could say that I am just giving an overview of the code. You should still gain an understanding of what different sections of the code do.

From there I move onto comparisons of NN using and not using things such as biases, and derivatives (yes, you can have a Neural Network without these things, although as you will see, they don't perform nearly as well).

Additionally, I explain what overfitting is and how it must be considered in making an ML model. I also briefly cover underfitting, however, the primary focus is on overfitting.

Рекомендации по теме
Комментарии
Автор

Great video. A question though, how do we avoid overfitting?

rolandray
Автор

Great job! Very informative and helpful.

JamesSmith-qqdd
Автор

Your videos are AWESOME, I have not been able to find anyone anywhere that both explain the mathematics behind NN's and shows a build up from the bottom how to make a real NN using python. Hats off man!
I had a bit of a rough time seeing how you made the maths into that chunk of code you used. In my opinion that could have been explained a bit more, but that might just be because i don't know the numpy lib well enough to understand what functions you are using xD
Thanks again for the great video!

davidludvigsen
Автор

Very well explained!
Congratulations boy!

FeKelvin
Автор

Great video! Just enough detail for me to get the gist.

marktwain