This project uses TensorFlow to build and train a neural network for classifying handwritten digits from the MNIST dataset. The model consists of a simple architecture with one hidden layer and a custom callback that stops training once the accuracy surpasses 99%.
- TensorFlow Implementation: Utilizes 'tf.keras' to create and train the model.
- Simple Model Architecture: Includes one hidden layer with ReLU activation.
- Custom Callback: Stops training when accuracy exceeds 99%.
- Data Normalization: Input data is normalized for better model performance.
The model achieves 99% accuracy on the training set.
- TensorFlow