This repository contains a simple implementation of a neural network model for recognizing handwritten digits from the MNIST dataset using TensorFlow and Keras. The model architecture consists of a flattening layer followed by two dense layers with ReLU activation functions and a final output layer with softmax activation.
Neural Network Recognizing hand-written digits
This Python script utilizes TensorFlow and Keras to create a neural network for classifying handwritten digits from the MNIST dataset. The MNIST dataset consists of 28x28 grayscale images of handwritten digits (0 to 9). The neural network is a simple feedforward model with three layers: a flattening layer, followed by two dense layers with ReLU activation, and a final dense layer with softmax activation for classification.
The model achieves high accuracy on the test set, demonstrating its effectiveness in classifying handwritten digits. The training accuracy graph shows the model's improvement over epochs. The final test accuracy is printed, and the model's prediction for a specific test image is displayed.
This script serves as a comprehensive example of building, training, and evaluating a neural network for digit classification using TensorFlow and Keras.