Kaggle - Digit Recognizer - CNN 99.4% Accuracy

Imaged below is the basic Convolutional Neural Network (CNN) for the Kaggle - Digit Recognizer competition.

Digit Recognizer - Convolutional Neural Network

Digit Recognizer - Convolutional Neural Network

Below provides an overview ensembling the CNN model. With executing the fit_model function 5 times, a total of a 125 epochs were executed.

Digit Recognizer - CNN-Ensemble.png

Running predictions against the test set for each model and averaging the prediction for each image.

Digit Recognizer - CNN - Predict.png

After exporting and submitting results, the basic CNN achieved 99.4% accuracy.

Digit Recognizer _ Kaggle-Submission.png

Kaggle - Invasive Species Monitoring - Ensemble with ROC of 0.95532

Ensemble (Bucket of models) multiple models to achieve ROC of 0.95532.

2017-09-25 Invasive Species Monitoring _ Kaggle.png

Below is an example of creating 4 models that were trained for 100 epochs each. The last section of code saves the weights for each model in the set. 

Invasive Species - CNN-BN-Ensemble.png

Each model was then used to predict the test image set. The mean prediction for each image was then used for the Kaggle Invasive Species Monitoring competition submission.