Full course description
Welcome to the entrance exam for the 100% online section of CSCI P556: Applied Machine Learning offerred through the Luddy School of Informatics, Computing, and Engineering. You must receive a satisfactory score on the timed exam in order to gain permission to enroll in the course each Fall and Spring terms.
The course is limited to 40 students each term, and seats will be allocated on a first-come, first-serve basis to those who meet the prerequisite knowledge and skills tested in this exam.
Those whom successfully score 6 or higher on the entrance exam may receive permission to enroll in CSCI P556: Applied Machine Learning for the upcoming or current term.
Please forward a copy of your passing score to the Luddy Office of Online Education via email at firstname.lastname@example.org. Their office will grant permission for enrollment; you will still need to register for the class through the normal channels.
Module Topics Include
There are three parts to this site, and you must access them in order:
- Survey of Machine Learning and programming experience
- Instructions for the examination (this is not timed; take all the time you want here)
- 45-minute timed exam (timed exercise)
The 45-minute timed exam will have three question types:
- Knowledge test: typically multiple choice
- Math (solve some simple math stuff)
The questions will focus on the following areas:
- Python programming skills (arrays, lists, strings, dictionaries, counting, functions)
- Basic probability theory (e.g., conditional probabilities)
- Basic calculus (derivatives of simple univariate functions; chain rule)
- Calculus review with a primary focus on the chain rule
- Basic derivative rules: https://www.khanacademy.org/math/ap-calculus-ab/ab-differentiation-1-new/modal/v/derivative-properties-and-polynomial-derivatives (Links to an external site.)
- Chain rule: https://www.khanacademy.org/math/ap-calculus-ab/ab-differentiation-2-new/ab-3-1a/v/chain-rule-introduction (Links to an external site.)
- Conditional probability theory review
- A tutorial on basic Python is provided here. There is no need to focus on Numpy nor on MatPlotLib at this time.
Meet the Instructor
Dr. James G Shanahan is an Adjunct Professor of Informatics and Computing at the Luddy School. He has spent the past 25 years developing and reseraching cutting-dege artificial intelligent systems, splitting his time between industry and academia. Dr. Shanahan has been affilated witht he University of California at Berkeley and at Santa Cruz since 2008, where he teaches graduate courses on big data analytics, machine learning, deep learning, and stochastic optimization. He has published six (6) books, more than 50 research publications, and over 20 patents in the areas of machine learning and information processing.
Contact the Luddy Office of Online Education for more information.