This repository contains a Jupyter notebook for digit recognition using machine learning techniques. The notebook covers data preprocessing, model training, and evaluation using the MNIST dataset.
The Digit Recognition project aims to recognize handwritten digits using machine learning. The notebook demonstrates the complete workflow, from data loading and preprocessing to model training and evaluation.
The dataset used in this project is the MNIST dataset, which can be found on Kaggle. It contains images of handwritten digits along with their corresponding labels.
To run the notebook, you need the following libraries:
pandas numpy matplotlib seaborn scikit-learn tensorflow (or keras)
The notebook includes the following steps:
Data Loading: Load the MNIST dataset. Data Preprocessing: Normalize the images and convert labels to categorical format. Model Training: Train a convolutional neural network (CNN) on the processed data. Model Evaluation: Evaluate the model's performance using accuracy score and other metrics. Visualization: Visualize the model's predictions and accuracy.
Contributions are welcome! If you have any suggestions or improvements, please open an issue or create a pull request.