Skip to content

This project aimed to write perceptron and neural network classes from scratch, and then use them on classic toy problems such as linear/non-linear function approximation and digit recognition using the MNIST dataset.

License

Notifications You must be signed in to change notification settings

Immodal/neural-network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

neural-network

This project aimed to write perceptron and neural network classes from scratch, and then use them on classic toy problems such as linear/non-linear function approximation and digit recognition using the MNIST dataset.

The app can be found here: https://immodal.github.io/neural-network/

Handwritten digit recognition

Figure 1: Handwritten digit recognition

Linear Function Approximator

Figure 2: Linear Function Approximator

About

This project aimed to write perceptron and neural network classes from scratch, and then use them on classic toy problems such as linear/non-linear function approximation and digit recognition using the MNIST dataset.

Topics

Resources

License

Stars

Watchers

Forks