🧠 MNIST Digit Classifier — ANN (Scikit-learn)

This project is part of the Infosys Springboard's module (Introduction to Deep Learning) in the AI & ML domain.

It demonstrates how to build a basic Artificial Neural Network (ANN) to classify handwritten digits from the MNIST dataset, using Scikit-learn’s MLPClassifier.

---

🔍 What It Does

• Loads digit images as pixel data (0–255 grayscale)
• Trains a neural network with 1 hidden layer (50 neurons)
• Predicts digit classes (0 to 9)
• Evaluates model using precision, recall, and F1-score

---

⚙️ Tools Used

• Python
• Jupyter Notebook
• Scikit-learn
• Pandas, NumPy, Matplotlib

---

🚀 How to Run

• Clone or download this repo

• Open the .ipynb notebook in Jupyter Notebook or JupyterLab

• Make sure the following libraries are installed:

  pip install numpy pandas matplotlib scikit-learn

• Run the notebook cell by cell to train and evaluate the ANN model.

📈 Output

• Achieved ~99% accuracy on the training data

• Learned the core concepts of neural networks, image preprocessing, and model evaluation

• A great first step before advancing to Convolutional Neural Networks (CNNs)