Master the essential techniques to assess LLM outputs and build more effective, ethically responsible AI solutions.
This course provides a framework for assessing large language model performance to meet operational and innovation standards. It examines evaluation methodologies ranging from foundational approaches to automated metrics and comparative analysis techniques. The curriculum covers the practical integration of human judgment alongside model-based assessment for both text and non-text generative outputs. Additionally, it highlights specific tools within the Vertex AI ecosystem and discusses the ethical requirements for maintaining reliable AI systems.
Topics Covered:
5 activities • 13 videos • duration: 1h 10m
AI Researcher & Educator, PhD in Computer Science, Director of AI Atelier, Generative AI Trustworthy AI
Dr. Reza Moradinezhad is an AI researcher, educator, and Assistant Teaching Professor at Drexel University's College of Computing & Informatics. With a PhD in Computer Science, his expertise spans Generative AI, Large Language Models (LLMs), Trustworthy AI, Human-AI Interaction, and Software Engineering. As Director of AI Atelier, he leads initiatives focused on AI education, research, and community engagement. His online courses on platforms including Udemy and Coursera have reached tens of thousands of learners worldwide, helping students and professionals develop practical AI skills. Beyond academia, Reza has industry experience as a Founding AI Scientist at TulipAI, where he worked on generative AI technologies and real-world applications. His teaching philosophy emphasizes bridging the gap between theory and practice. Through clear explanations, real-world examples, and hands-on learning, he helps professionals not only understand emerging AI technologies but also evaluate, implement, and use them effectively and responsibly.
