The problems are part of Mlabs: A Machine learning focused accelerator program
The four problems are briefly discussed below.
-
Gradient Descent: This is a popular optimization problem to find solutions to differentiable equations. Typically, learning problems involve minimizing a cost function by appropriately setting model parameters. In this task, we are given a set of (noisy) points on a line and we wish to retrieve model parameters (intercept and slope) through gradient descent.
-
Eigenfaces: This is a popular application of learning a basis representation of input data. The application of this technique is the basis for simple recognition/compression algorithms. In this task, we want to learn orthonormal basis using PCA of images that correspond to faces.
-
Classification: This is among the basic tasks of machine learning problems. Here, we will learn a classifier to using groundtruth labels on the training data to be able to distinguish between two object classes.
-
Disparity map: This is among the basic tasks of 3D computer vision Here, given two different perspectives of the same scene, we will reconstruct an approximate of the depth map. This is called the disparity map (higher disparity is similar to lower depth). Scikit library is used to implement the module.