In this homework, you will work on pattern recognition problems that require position invariance. Specifically, you will work on the problem of verifying faces in images. In typical pictures of faces, the face is rarely perfectly centered. Different pictures of the same person may have the face shifted by varying amounts. The classifier must recognize the face regardless of this indeterminacy of position. This calls for position-invariant models, specifically Convolutional Neural Networks, or CNNs.

Face verification refers to the task of determining whether two face images are of the same person, without necessarily knowing who the person is. Face verification is an instance of a larger class of problems where we attempt to determine if two data instances belong to the same class without necessarily knowing (or having a model for) the class itself.