Crate corgi[−][src]
Machine learning, and dynamic automatic differentiation implementation.
Modules
| activation | An activation function is a non-linear function applied to the output of a layer. |
| array | An n-dimensional array, with automatic differentation. |
| initializer | A weight initializer. |
| layer | A layer of a neural network. |
| layers | Implementations of neural network layers. |
| model | A supervised neural network model, which computes a forward pass, and updates parameters based on a target. |
| numbers | Floating point type wrapper, which may be changed to |
| optimizer | An optimizer updates the parameters of a model. |
| optimizers | Implementations of gradient descent optimizers. |
Macros
| arr | Creates an |