A python package for building feed forward neural networks. The neural networks can contain any number of nodes in each layer. Each neural network has an input layer, an output layer and any number of hidden layers. Each layer can use either a sigmoid or tanh activation function. The cost function used is mean squared error. The builder class can be used to initialize a network with any number of input and output nodes and any number of hidden layers with any number of nodes per hidden layer.
-
Notifications
You must be signed in to change notification settings - Fork 0
Ca1eb3/NeuralNetwork
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
An implementation to build neural networks
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published