Skip to content

benclarkegithub/introduction-to-neural-networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Introduction to Neural Networks

For the presentation "An Intuitive Introduction to Neural Networks" given at Bank of America. IntroductionToNeuralNetworks.ipynb trains and visualises the weights of a neural network with one hidden layer trained on the MNIST dataset.

For reference, a logistic regression model trained on MNIST might have the following weights (source):

The weights of a logistic regression model trained on MNIST visualised.

In contrast, the weights of the input layer to the hidden layer of a neural network trained on MNIST:

The weights of the input layer to the hidden layer of a neural network trained on MNIST visualised.

And, the weights of the hidden layer to the output units 0 and 1:

The weights of the hidden layer to the output units 0 and 1 of a neural network trained on MNIST visualised.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published