Lecture (LEC)

• TOPIC: REINFORCEMENT LEARNING
• Above class meets with a section of CSCI-B 490

Topic: Reinforcement learning

Lecture (LEC)

• Above class meets with LING-L 665

Topic: Applying ml techniques in cl

Lecture (LEC)

• TOPIC: Advanced Machine Learning for CL
• Above class meets with a section of LING-L 715

Topic: Adv. machine learning for cl

Lecture (LEC)

• TOPIC: TBD
• Above class meets with a section of LING-L 715

Lecture (LEC)

• TOPIC: TBD
• Above class meets with a section of LING-L 715

Lecture (LEC)

• TOPIC: Trustworthy Machine Learning

Topic: Machine learning

Course Name/Topic: Trustworthy Machine Learning (TML) Machine learning (ML) is extensively employed to enhance various practical tasks, but it also poses challenges related to trustworthiness. Key risks include susceptibility to various malicious attacks that can skew prediction outcomes, its opaque and complex nature that makes it difficult to interpret, and potential breaches of privacy and fairness norms. This course highlights these trustworthiness issues in machine learning with a focus on robustness, interpretability, privacy, and fairness. We discuss different attack and defense methods and promote awareness about the implications of using ML models for critical tasks. This course will require intensive ML programming in the Python programming language. The course will include both lectures and in-depth discussion on research papers. Learning Objectives and Outcomes. In this course, students will: ¿ Acquire knowledge on different TML issues, including adversarial attacks and defenses, model explanations, and possible violations of fairness ¿ Examine how these issues apply to a variety of commonly used ML algorithms ¿ Explore different mitigation strategies to address TML issues ¿ How to effectively read, digest ML research papers You are expected to (i) be very familiar with the Python programming language, basic probability theory, and basic calculus/discrete math, and (ii) a good understanding of ML and (iii) a basic understanding of neural-network and deep-learning algorithms. Textbook: No required textbooks. All class materials will be publicly available to the students.

Lecture (LEC)

• B 659 : P - INFO-I 519 or BIOL-L 519 or consent of instructor
• Above class meets with INFO-I 529

Topic: Machine learning bioinformatic

Laboratory (LAB)

• Above class meets with INFO-I 529

Topic: Machine learning bioinformatic