Computer Science Microprogram Courses
Description:
The course provides participants with practical expertise in machine learning by maintaining a strong focus on hands-on experience and emphasizing project-oriented learning. Topics include data preparation, regression, classification, supervised learning, unsupervised learning, semi-supervised learning. Methods include linear models, nearest neighbours, support vector machines, random forests, and boosting. Software tools include the Python ecosystem and scikit-learn, and projects target mainly tabular data.
Component(s):
Lecture; LaboratoryDescription:
The course provides participants with practical expertise in deep learning by maintaining a strong focus on hands-on experience and emphasizing project-oriented learning. Topics include multi-layer perceptrons, commonly used deep learning model architectures, loss functions, regularization, and optimization methods. Software tools include PyTorch, Jax, and Tensorflow. Projects target mainly computer-vision (image or video) or natural-language data.