This course explores the emerging field of neurosymbolic knowledge graphs, which combines deep learning techniques with symbolic reasoning to tackle complex knowledge representation and reasoning tasks. Students will delve into the theoretical foundations and practical applications of neurosymbolic knowledge graphs, including the integration of neural networks with symbolic knowledge bases, hybrid knowledge graph construction, explainable AI, and more. Through lectures, hands-on projects, and discussions, students will develop the skills to design and implement cutting-edge models for neurosymbolic knowledge graph analysis and manipulation.
Assessment Criteria
- Via written papers
- Via oral (individual) presentations
- Via participation in class
- Late submission policy: first time with valid reason – no penalty, otherwise 20% of score deducted each late day.
Attendance
Attendance at all classes is expected. If you are sick and can not attend, please contact the professor in advance. The class includes many group participation activities and participation in class is included in the final grade evaluation. Missed classes are recorded and will impact grades.
Academic Integrity
The Rensselaer Handbook of Student Rights and Responsibilities and The Rensselaer Graduate Student Supplement define various forms of Academic Dishonesty and procedures for responding to them. All forms are violations of the trust between students and teachers. Student-teacher relationships are built on trust. For example, students must trust that teachers have made appropriate decisions about the structure and content of the courses they teach, and teachers must trust that the assignments that students turn in are their own performance. Acts that violate this trust undermine the educational process.
The Rensselaer Handbook of Student Rights and Responsibilities and The Rensselaer Graduate Student Supplement define various forms of Academic Dishonesty and you should make yourself familiar with these. In this class, all assignments that are turned in for a grade must represent the student’s own work. In cases where help was received, or teamwork was allowed, a notation on the assignment should indicate your collaboration. Submission of any assignment that is in violation of this policy will result in a penalty. If found in violation of the academic honesty policy, students may be subject to two types of penalty. The instructor administers an academic [grade] penalty and the student is reported to the Dean of Students or the Dean of Graduate Education as appropriate. The first violation results in 0 grade for that assignment. The second violation results in failure of the course. If you have any questions concerning this policy before submitting an assignment, please ask for clarification.
Use of Generative AI (Chat GPT and similar)
Unattributed use of generative AI for assignments and other coursework is considered plagiarism and will be penalized accordingly. Credited use of generative AI for coursework that fulfills assessment criteria and has not been demonstrated by the student will not count towards fulfilling the assessment criteria. Any criteria that are not demonstrated by the student themselves will be counted as a missed, or 0 score.
Students with Disabilities
Rensselaer Polytechnic Institute strives to make all learning experiences as accessible as possible. If you anticipate or experience academic barriers based on a disability, please let the instructors know immediately so that we can discuss your options. To establish reasonable accommodations, please register with The Office of Disability Services for Students. After registration, make arrangements with us as soon as possible to discuss your accommodations so that they may be implemented in a timely fashion. DSS contact information: dss@rpi.edu; 518-276-819; 4226 Academy Hall.
Course: Topics in Knowledge Graphs
Date: to