Artificial Neural Network (ANN) from Scratch using NumPy on MNIST Dataset

Features

• Built a customizable neural network with any number of layers and neurons.
• Used ReLU activation for hidden layers and Softmax for outputs.
• Implemented forward and backward propagation with gradient descent.
• Used cross-entropy loss for classification.
• One-hot encoded the target labels.

Prerequisites

• Python 3.x
• NumPy
• Matplotlib
• Tensorflow
• Keras

Getting Started

1. Clone the repository:

   https://github.com/Sam783/ANN_MNIST.git

2. Install the required dependencies:

   pip install -r requirements.txt