Modified MNIST Challenge
For project #3, you are asked to create classifiers to analyze images consisting of two digits and a character. The character may be an 'a'  or 'A' (for add), in which case your classifier has to return the sum of the two digits,  or an 'm'  or 'M' (for multiply), in which case your classifier has to return the product of the two digits. Additionally, a variety of different textures are used in the backgrounds of the images.
We provide a set of labeled training data (images and target outputs) as well as a set of unlabeled test data (i.e. images only).  You must run your model on the test data and submit the target outputs to Kaggle.
You are allowed to use libraries such as theano/sklearn/tensorflow/pytorch
for parts 3 and 1 only
. For part 2 you must do the full implementation. You can submit any part for kaggle, although the kaggle competition is ranked based on your best submission only and you have a daily limit on number of submissions.
Please keep the kaggle teams the same as the teams for the report, and include your kaggle team name in the report so we can grade your performance  :)