shebna12 / ANN-from-scratch

A Python implementation of Artificial Neural Networks from Scratch

ANN-from-scratch

A Python implementation of Artificial Neural Networks(ANNs) from Scratch.

Notes

• This has only two hidden layers.
• This implementation uses the sigmoid activation function.
• Stopping criterion depends on the set threshold.

Parameters

• n_h1 = number of nodes for the first hidden layer
• n_h2 = number of nodes for the second hidden layer
• eta = learning rate parameter
• max_epoch maximum number of iterations
• thresh = threshold, if cost function is less than the threshold, stop the training process.