A Mathematica implementation of differential equations that describe the macroscopic on-line gradient descent learning dynamics for (so far) two layer neural networks. The hidden units can use sigmoidal or ReLU activation.
-
Notifications
You must be signed in to change notification settings - Fork 0
MichielStraat/Macroscopics_NeuralNets
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A Mathematica implementation of differential equations that describe the macroscopic on-line gradient descent learning dynamics for the Soft Committee Machine.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published