Courses and Syllabi
The Computational Brain Science group is actively developing a new curriculum in Computational Neuroscience and Data Science in general. Here a list of relevant classes that are currently being taught:
This class covers the basic principles of Data Science and Machine Learning. It is designed for students from various backgrounds. The class is being taught twice a year, both in the fall (A) and winter term (B). Our teaching philosophy is that theoretical knowledge (why am I doing this?) and practical skill (how am I doing this?) are intimately interconnected. Therefore, every week, the class has a 2-hr lecture that covers the basic principles, and a 2-hr tutorial that shows how to implement the corresponding techniques in Python. Weekly homework assignments broaden and deepen these skills. Assessments focus on the ability to apply the this knowledge to a new data set. After all, it does not matter what we theoretically know, but only what we actually can do.
Computational neuroscience is an exciting and developing field, with rapidly growing applications in technology and industry. Researchers in this field employ numerical modeling techniques and mathematical approaches to answer fundamental questions about neural structure, dynamics, and computation. This one-semester course will provide students with an introduction to computational neuroscience. Students will learn fundamentals of neural computation and explore how networks of neurons support information processing in the brain. Through this material, students will become familiarized with computational modeling, programming, and machine learning techniques.
CS9542B / CS4442: Artificial Intelligence II (Mohsenzadeh / Wang)
This course is a continuation of CS3346, Artificial Intelligence I. A broad range of areas falls into the field of Artificial Intelligence. This course introduces two very active areas of Artificial Intelligence: machine learning and computer vision, covering topics from early, to mid- and high-level vision, including basics of machine learning and deep convolutional neural networks for vision. The course covers both algorithmic perspectives of artificial intelligence and their practical applications in computer vision.
