MLP-Numpy
A simple modular implementation of Multi Layer Perceptron in pure Numpy. I used the Iris dataset from scikit-learn library for the experiments.
Features
- Fully modular and configurable
- Different learning rates can be used for different layers and iterations. (Dynamic learning rate)
- Pure numpy with no additional dependecies
- Supports Linear, Softmax, Sigmoid, TanH, and ReLU activations