Digit Recognizer - MNIST
This repository focuses on digit recognition using two different approaches:
- Deep Learning with Keras: Achieves an accuracy of approximately 99%.
- Machine Learning with scikit-learn: Achieves an accuracy of about 95%.
The dataset used for this project is the Digit Recognizer Dataset from Kaggle.
MNIST: Introduction to Convolutional Neural Network (CNN) with Keras
Table of Contents:
- Introduction
- Data Preparation
- Load data
- Normalization
- Reshape
- Label encoding
- Split training and validation set
- Convolutional Neural Network
- Define the model architecture
- Data augmentation
- Model training
- Evaluate the Model
- Training and validation curves
- Confusion matrix
- Prediction and Submission
- Prediction validation results
- Submission
- References
MNIST: Simple Machine Learning Algorithms
Table of Contents:
- Introduction
- Machine Learning Algorithms
- Random Forest Classifier
- KNeighborsClassifier
- Naive Bayes
- Submission
You can copy and edit the code directly from my Kaggle notebooks:
If you find this project helpful or interesting, please don't forget to upvote it!
© 2023 elcaiseri