Skip to content

Instantly share code, notes, and snippets.

@ludennis
Last active February 6, 2018 04:51
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ludennis/eb91c2be3cbde312b9dab0172aee44a1 to your computer and use it in GitHub Desktop.
Save ludennis/eb91c2be3cbde312b9dab0172aee44a1 to your computer and use it in GitHub Desktop.
---
#Deep Learning (Neural Networks)
A day prior to my Deep Learning nanodegree foundation begins, I try to prep myself as much as possible for the topics that are to be covered. And I stumbled upon Welch Labs YouTube Channel with 7 parts of their videos to explain and code Deep Learning Neural Networks in Python with a simple case.
---
Coding a neural network to learn it
So I thought of how I, as a kinesthetic learner, can learn neural network, and I thought of just trying to work out the same example given in the first part of neural networks from Welch Labs:
Input(Hours of Sleep, Hours of Study) -> Output(Score on Test)
(3,5) -> 75
(5,1) -> 82
(10,2) -> 93
(8,3) -> ?
A process of normalization would have to take place for each data:
x_norm = x / max(x)
y_norm = y / max(y) #max(y)=100 since the highest score is 100
Photo captured from Welch Lab’s Neural Networks DemystifiedBefore Coding, I would need
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment