In this project, I built a simple neural network using Keras to classify handwritten digits from the MNIST dataset. The model achieved an accuracy of approximately 97.2% on the test dataset after training for 10 epochs. The code demonstrates loading and preprocessing the data, defining the neural network architecture, compiling the model with appropriate loss and optimizer, and evaluating its performance. It helped me learn about image classification with neural networks using Keras and TensorFlow.
nujoum / mnist-handwritten-digits-classification-with-keras Goto Github PK
View Code? Open in Web Editor NEWSimple neural network using Keras to classify handwritten digits from the MNIST dataset