In this assignment, you will develop a deep learning system for the classification of images containing decimal digits into three categories:
- A-digit 0
- B-digit 1
- C-others (e.g. any digit in 2,3,4,5,6,7,8,9)
For this purpose, you will use the MNIST dataset. (Download Here) (Links to an external site.)
You will develop your solution within a transfer learning paradigm. Rather the designing and training a deep learning system from the scratch, you can use the Internet to find solutions to start from and/or augment. (HINT: There are many models in Python that can be found online to solve this problem.)
- Download and arrange a subset of the MNIST data in the three categories above, performing the proper partition into training, validation and testing
- Design, train, validate and test a model
- Compare and interpret the performance of each model (accuracy, behavior of the validation versus training, etc).
Note: Ensure you explain the rational and the methodology for tasks 1 and 2.
This is meant to be fun, challenging, and a stretch assignment. Effort is what matters, not the perfect solution!!!