Constructed an Artificial Neural Network on the Churn dataset with 10,000 observations/rows and 14 attributes.
Constructed a Convoluted Neural Network on the MNIST dataset which is a database of handwritten digits with a training set of 60,000 examples and a test set of 10,000 examples. The digits have been size-normalized and centered in a fixed-size image and MNIST is considered to be a very good dataset for beginners who want to learn pattern recognition methods on real-world data while spending minimal efforts on preprocessing.