CN7023: Design, implement and deploy a deep learning based custom image multi-class classifier

Task

Design, implement and deploy a deep learning based custom image multi-class classifier. Write a research report of 5000 words in the style of a research paper, including the following:

• The research question(s) you are exploring and the experiments you designed to address these question(s).
• A clear presentation of the methods (implementation, architectures, hyper parameters.) that were used, an outline of how they were deployed, and a justification of your decisions.
• A clear presentation of results, discussion and interpretation of results and conclusions.
• Please follow the marking scheme and to ensure your report includes all required sections.

Datasets

Here are some online dataset repositories, or come up with your own:

• UCI KDD Archive : http://kdd.ics.uci.edu/
• UCI Machine Learning Repository:
• NIST Handprinted Forms and Characters Database https://www.nist.gov/srd/nist-special-database-19
• The mixed National Institute of Standards and Technology (MNIST) data set https://msdn.microsoft.com/en-us/magazine/dn754573.aspx
• CIFAR-10: http://groups.csail.mit.edu/vision/TinyImages/