Imaged below is the basic Convolutional Neural Network (CNN) for the Kaggle - Digit Recognizer competition.
Below provides an overview ensembling the CNN model. With executing the fit_model function 5 times, a total of a 125 epochs were executed.
Running predictions against the test set for each model and averaging the prediction for each image.
After exporting and submitting results, the basic CNN achieved 99.4% accuracy.