Image Recognition is a central task in computer vision with applications ranging across search, robotics, self-driving cars and many others. There are three purposes of this document: 1. We follow up on (Fischetti & Jo, December, 2017) and show how standard convolutional neural network can be optimized to a more sophisticated capsule architecture. 2. We introduce a MILP model based on CNN to create adversarials. 3. We compare and evaluate each network for image recognition tasks.
View on arXiv