Admission requirements
Archaeological Science Specialisation Course: Computational Archaeology obtained.
Students who have not attended the “Archaeological Science Specialisation Course: Computational Archaeology” are expected to pass a short entry test for admission.
Description
The course introduces students to some of the core concepts in machine learning, a sub-field of artificial intelligence, at a beginner level. Using archaeological data, students apply their coding skills to understand the computational basics of algorithms. In the course, students will also read and assess published scholarly work relevant to machine learning in archaeology. Through assigned readings, students will discuss their findings in class meetings.
Course objectives
The course has two main aims. The first is to provide working knowledge and computational basics of machine learning. The curriculum covers core concepts such as supervised and unsupervised classification. Students also learn valuable tools and algorithms, such as k-means clustering and random forest and apply these tools to archaeological data. Second, it offers scholarly readings on how machine learning (ML) and artificial intelligence (AI) are utilized in archaeological research. Students completing this course will acquire skills to practice the basics of machine learning and artificial intelligence in archaeology. They will also be able to reflect on those applications.
Timetable
Course schedule details can be found in MyTimetable.
Log in with your ULCN account, and add this course using the 'Add timetable' button.
Mode of instruction
The course has two main modules. In the first module, lecturers present the course material in a class and supervise hands-on coding practices in dedicated lab sessions. In the second module, lecturers guide students in general debates and offer means for reflexive discussions in the class.
Assessment method
There are two assessments:
Assessment 1 - Reflection - (50%): Students will critically evaluate an existing ML/AI study, write a detailed peer review (30%), and present the study in class (20%), focusing on the strengths and weaknesses of the methodology.
Assessment 2 - Project - (50%): Students tackle a classification/prediction problem using ML/AI.
Reading list
Lecturers will periodically assign readings for the in-class discussions. The final reading list will be published before the class based on the number of registered students in the course.
Registration
Students are required to register themselves for all components of a course, including lectures, tutorials, practicals, exams, and resits through MyStudymap. This applies to both compulsory elements and elective credits. If you are not enrolled, you may not participate.
General information about registration can be found on the Course and exam enrolment page.
Contact
For more information about this course, please contact Dr. T. (Tuna) Kalaycı.
Remarks
Attendance is compulsory. Students are expected to use their laptops.