# [[👤Roman Yampolskiy]] - [[Artificial Intelligence]] - [[👤Roman Yampolskiy]] *** Roman Yampolskiy is a prominent computer scientist and researcher specializing in artificial intelligence (AI) safety and security. Here are some key points about his background and work: 1. Academic Position: - Associate Professor in the Department of Computer Science and Engineering at the University of Louisville's Speed School of Engineering[2][6] - Director of the Cyber Security Laboratory at the University of Louisville[1][2] 2. Education: - PhD in Computer Science and Engineering from the University at Buffalo (2008)[2][5] - BS/MS (High Honors) in Computer Science from Rochester Institute of Technology[2][5] 3. Research Focus: - AI safety and security, particularly concerning advanced and superintelligent AI systems[1][4] - Behavioral biometrics, digital forensics, and pattern recognition[2] - Limits of control, explainability, predictability, and controllability of advanced AI systems[8] 4. Publications: - Author of over 100 publications, including journal articles and books[2][11] - Notable books include "Artificial Superintelligence: A Futuristic Approach" (2015) and "AI Safety and Security" (2018)[7][12] 5. Recognition and Affiliations: - Fellow of various institutions, including the Machine Intelligence Research Institute (MIRI) and the Foresight Institute[12] - Research Associate of the Global Catastrophic Research Institute (GCRI)[12] - His work has been featured in numerous media reports and translated into multiple languages[2][10] 6. Contributions to AI Safety: - Advocates for responsible AI development and research into potential risks of advanced AI systems[1][4] - Developed concepts related to AI containment and analysis of AI accidents[12] - Focuses on theoretical limits of AI explainability, predictability, and controllability[12] 7. Public Engagement: - Given over 100 public talks on AI safety[12] - Frequently interviewed on AI safety topics, including appearances on podcasts[12] - Known for presenting complex AI concepts in an accessible and sometimes humorous manner[8] 8. Teaching: - Highly rated professor by students, known for clear and engaging lectures[3] - Teaches courses related to computer science and AI at the University of Louisville[3] Roman Yampolskiy is considered a leading expert in the field of AI safety, contributing significantly to academic discourse and public understanding of the potential risks and challenges associated with advanced AI systems. Citations: [1] https://en.wikipedia.org/wiki/Roman_Yampolskiy [2] https://engineering.louisville.edu/faculty/roman-v-yampolskiy/ [3] https://www.ratemyprofessors.com/professor/1388970 [4] https://twitter.com/romanyam [5] https://www.linkedin.com/in/romanyam [6] https://deepfest.com/roman-yampolskiy-0 [7] https://scholar.google.com/citations?hl=en&user=0_Rq68cAAAAJ [8] https://speakabout.ai/roman-yampolskiy [9] https://philpeople.org/profiles/roman-yampolskiy [10] http://cecs.louisville.edu/ry/ [11] https://www.researchgate.net/profile/Roman-Yampolskiy [12] https://futureoflife.org/person/prof-roman-yampolskiy/ [13] https://www.routledge.com/authors/i8581-roman-yampolskiy