Convolutional Neural Network
- Problem Definition
Our goal is to build a machine learning model that classifies 5 different types of skin cancers with best accuracy possible based on the skin images which were provided to us. These cancer types are: Melanoma (MEL), Melanocytic nevus (NV), Basal cell carcinoma (BCC), Actinic keratosis (AK), Benign keratosis (BKL).
For further information about the project, please take a look at the CS412 Project Report file.
Kaggle Competition link: https://www.kaggle.com/c/machinelearning412-skincancerclassification/overview
Note: We became 2nd among the 23 groups in the competition with 81.66% classification accuracy.