A collections of classes that implement a Neural Network from scratch. The value class contains the value of one neuron including its gradient. It performs the calculations needed for back propagation. The Value class is then wrapped in a neuron class. The input weights, bias and output are all included in this. The neuron is in turn wrapped in the layer class that contains all of the neurons of one layer. This is turn is wrapped in the multi layer perception
-
Notifications
You must be signed in to change notification settings - Fork 0
A collections of classes that implement a Neural Network from scratch. The value class contains the value of one neuron including its gradient. It performs the calculations needed for back propagation. The Value class is then wrapped in a Neuron class which is in turn wrapped in the Layer class which is in turn wrapped in the MLP class.
steven7/micrograd_clone
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A collections of classes that implement a Neural Network from scratch. The value class contains the value of one neuron including its gradient. It performs the calculations needed for back propagation. The Value class is then wrapped in a Neuron class which is in turn wrapped in the Layer class which is in turn wrapped in the MLP class.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published